{
  "artifact_type": "operational_coverage_audit",
  "files": [
    {
      "mtime_ns": 1786109829778739077,
      "path": "gdelt_gkg/leg=media/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 36664,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5602982,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617880603107,
      "path": "documents/leg=media/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 265,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 857706,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616750430586,
      "path": "documents/leg=institutional/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1275,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1210972,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786109909717080248,
      "path": "passages/leg=media/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 6560,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1056723,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786109909669542520,
      "path": "passages/leg=institutional/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 8253,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1235511,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785926968727800925,
      "path": "embeddings/leg=media/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 226,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 189629,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785926968665213902,
      "path": "embeddings/leg=institutional/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1275,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 972774,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616082277082,
      "path": "spans/leg=media/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616080986957,
      "path": "spans/leg=institutional/ym=2022-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785825060543254304,
      "path": "gdelt_gkg/leg=media/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 56206,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 9566938,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617893485544,
      "path": "documents/leg=media/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 357,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1249961,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616775530415,
      "path": "documents/leg=institutional/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1833,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1692166,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785825140117577593,
      "path": "passages/leg=media/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 10332,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1710974,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785825140012112595,
      "path": "passages/leg=institutional/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 10948,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1713535,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785926968733781324,
      "path": "embeddings/leg=media/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 312,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 266577,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785926968697941222,
      "path": "embeddings/leg=institutional/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1833,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1381340,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616088899081,
      "path": "spans/leg=media/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616087921289,
      "path": "spans/leg=institutional/ym=2022-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785837149834782121,
      "path": "gdelt_gkg/leg=media/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 35358,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5778782,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617902940798,
      "path": "documents/leg=media/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 291,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1099787,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616794607799,
      "path": "documents/leg=institutional/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1205,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1044797,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785837219373288141,
      "path": "passages/leg=media/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 10693,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1732045,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785837219262791384,
      "path": "passages/leg=institutional/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 6638,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1049076,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129227108682,
      "path": "embeddings/leg=media/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 243,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 201957,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129163617877,
      "path": "embeddings/leg=institutional/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1205,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 921535,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616094874622,
      "path": "spans/leg=media/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616093845830,
      "path": "spans/leg=institutional/ym=2022-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785859590387246161,
      "path": "gdelt_gkg/leg=media/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 28164,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4511511,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617910765127,
      "path": "documents/leg=media/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 243,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 864586,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616818796290,
      "path": "documents/leg=institutional/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1623,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1400551,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785859635708623514,
      "path": "passages/leg=media/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 8778,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1232729,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785859635654590026,
      "path": "passages/leg=institutional/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 8879,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1412937,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129233505171,
      "path": "embeddings/leg=media/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 189,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 162609,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129192355370,
      "path": "embeddings/leg=institutional/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1623,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1227580,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616100402413,
      "path": "spans/leg=media/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616099506121,
      "path": "spans/leg=institutional/ym=2022-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785915529450274493,
      "path": "gdelt_gkg/leg=media/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 20756,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3268214,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617916834782,
      "path": "documents/leg=media/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 169,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 652950,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616840283227,
      "path": "documents/leg=institutional/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1494,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1245939,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785917118809708691,
      "path": "passages/leg=media/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 4731,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 718433,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785917118758323452,
      "path": "passages/leg=institutional/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 8265,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1253751,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129236804667,
      "path": "embeddings/leg=media/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 148,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 132185,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785931129220809027,
      "path": "embeddings/leg=institutional/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1494,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1131901,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616105388287,
      "path": "spans/leg=media/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616104302662,
      "path": "spans/leg=institutional/ym=2022-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785951124885206296,
      "path": "gdelt_gkg/leg=media/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 19859,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3018136,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617921519138,
      "path": "documents/leg=media/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 157,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 538348,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616859498403,
      "path": "documents/leg=institutional/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1269,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1095983,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785952436143065517,
      "path": "passages/leg=media/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 3201,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 582019,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785952436119421144,
      "path": "passages/leg=institutional/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 7398,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1100451,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785954910439051894,
      "path": "embeddings/leg=media/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 144,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 129135,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785954910435437692,
      "path": "embeddings/leg=institutional/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1269,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 967792,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616110793078,
      "path": "spans/leg=media/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616109725578,
      "path": "spans/leg=institutional/ym=2022-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785961776035297133,
      "path": "gdelt_gkg/leg=media/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 18979,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 2928646,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617925945826,
      "path": "documents/leg=media/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 151,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 508645,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616862899627,
      "path": "documents/leg=institutional/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 131,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 123362,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785962695619565736,
      "path": "passages/leg=media/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 3012,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 553793,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785962695601344167,
      "path": "passages/leg=institutional/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 1325,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 122699,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785962807636668003,
      "path": "embeddings/leg=media/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 135,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 122489,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785962807633665275,
      "path": "embeddings/leg=institutional/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 131,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 117180,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616114606411,
      "path": "spans/leg=media/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616113673745,
      "path": "spans/leg=institutional/ym=2022-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785977901495238066,
      "path": "gdelt_gkg/leg=media/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 20425,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3200543,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617930062429,
      "path": "documents/leg=media/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 159,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 463536,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616879782459,
      "path": "documents/leg=institutional/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1243,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1072242,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785979246836122238,
      "path": "passages/leg=media/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 2873,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 496281,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785979246814768479,
      "path": "passages/leg=institutional/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 7089,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1077657,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785981858894909828,
      "path": "embeddings/leg=media/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 137,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 124142,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785981858890678351,
      "path": "embeddings/leg=institutional/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1243,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 947654,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616119106786,
      "path": "spans/leg=media/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616118211577,
      "path": "spans/leg=institutional/ym=2022-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785986248576826579,
      "path": "gdelt_gkg/leg=media/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 24377,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3879362,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617934872910,
      "path": "documents/leg=media/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 179,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 581854,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616908242512,
      "path": "documents/leg=institutional/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2207,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1863347,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785987562493150962,
      "path": "passages/leg=media/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 3608,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 636267,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785987562466585475,
      "path": "passages/leg=institutional/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 10694,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1848925,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785988974292629555,
      "path": "embeddings/leg=media/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 164,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 144095,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785988974284135376,
      "path": "embeddings/leg=institutional/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2207,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1654373,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616124819868,
      "path": "spans/leg=media/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616123862618,
      "path": "spans/leg=institutional/ym=2022-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786004964394883672,
      "path": "gdelt_gkg/leg=media/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 17770,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 2829682,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617939109431,
      "path": "documents/leg=media/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 124,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 485777,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616930212076,
      "path": "documents/leg=institutional/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1663,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1408279,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786006149544173810,
      "path": "passages/leg=media/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 2771,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 523740,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786006149524623567,
      "path": "passages/leg=institutional/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 9117,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1434383,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786007230867442970,
      "path": "embeddings/leg=media/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 123,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 113323,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786007230863185101,
      "path": "embeddings/leg=institutional/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1663,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1256980,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616130439118,
      "path": "spans/leg=media/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616129456159,
      "path": "spans/leg=institutional/ym=2022-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786012953221012372,
      "path": "gdelt_gkg/leg=media/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 23019,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3505993,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617942932699,
      "path": "documents/leg=media/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 129,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 415113,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616946006944,
      "path": "documents/leg=institutional/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1258,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1037328,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786015700126050196,
      "path": "passages/leg=media/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 2595,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 449761,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786015700108308400,
      "path": "passages/leg=institutional/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 6732,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1036460,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786016751591257567,
      "path": "embeddings/leg=media/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 120,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 110982,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786016751585459520,
      "path": "embeddings/leg=institutional/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1258,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 960487,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616135103200,
      "path": "spans/leg=media/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616134167325,
      "path": "spans/leg=institutional/ym=2022-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786022901862522907,
      "path": "gdelt_gkg/leg=media/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 21673,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3280316,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617948009348,
      "path": "documents/leg=media/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 174,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 586191,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616961991188,
      "path": "documents/leg=institutional/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1248,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1098450,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786030955333109330,
      "path": "passages/leg=media/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 3361,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 632815,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786030955309839684,
      "path": "passages/leg=institutional/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 7154,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1105357,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786032881963357581,
      "path": "embeddings/leg=media/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 165,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 144814,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786032881952405115,
      "path": "embeddings/leg=institutional/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1248,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 952977,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616139870741,
      "path": "spans/leg=media/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616138952658,
      "path": "spans/leg=institutional/ym=2023-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786057362483562404,
      "path": "gdelt_gkg/leg=media/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 25533,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3807987,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617954454796,
      "path": "documents/leg=media/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 241,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 797964,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423616980241567,
      "path": "documents/leg=institutional/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1527,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1235142,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786058930293302344,
      "path": "passages/leg=media/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 5318,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 948962,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786058930259045469,
      "path": "passages/leg=institutional/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 8613,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1241285,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786060067015565935,
      "path": "embeddings/leg=media/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 212,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 179359,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786060067009445974,
      "path": "embeddings/leg=institutional/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1527,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1157238,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616145311199,
      "path": "spans/leg=media/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616144389949,
      "path": "spans/leg=institutional/ym=2023-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786094909619895978,
      "path": "gdelt_gkg/leg=media/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 27496,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4670782,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617961706289,
      "path": "documents/leg=media/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 271,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 896552,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617002875843,
      "path": "documents/leg=institutional/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1791,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1486868,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786095230706023848,
      "path": "passages/leg=media/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 5102,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 993313,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786095230672253332,
      "path": "passages/leg=institutional/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 10135,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1497909,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099270056765215,
      "path": "embeddings/leg=media/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 246,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 204034,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099269977092536,
      "path": "embeddings/leg=institutional/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1791,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1350385,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616153663031,
      "path": "spans/leg=media/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616152608323,
      "path": "spans/leg=institutional/ym=2023-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786102300779874626,
      "path": "gdelt_gkg/leg=media/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 28301,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5236713,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617968317863,
      "path": "documents/leg=media/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 265,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 784228,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617019171879,
      "path": "documents/leg=institutional/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1287,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1098586,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786103273942812605,
      "path": "passages/leg=media/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 4711,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 903790,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786103273906625569,
      "path": "passages/leg=institutional/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 7181,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1105394,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786103347681113279,
      "path": "embeddings/leg=media/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 230,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 192306,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099270001604835,
      "path": "embeddings/leg=institutional/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1287,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 981523,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616158981864,
      "path": "spans/leg=media/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616158005572,
      "path": "spans/leg=institutional/ym=2023-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786107039247998259,
      "path": "gdelt_gkg/leg=media/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 35437,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6719909,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617975819357,
      "path": "documents/leg=media/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 284,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 876173,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617038138346,
      "path": "documents/leg=institutional/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1517,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1303058,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786107108814801844,
      "path": "passages/leg=media/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 5886,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1036265,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786107108777681047,
      "path": "passages/leg=institutional/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 8478,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1313823,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786101499092330114,
      "path": "embeddings/leg=media/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 248,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 205410,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099270028488313,
      "path": "embeddings/leg=institutional/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1517,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1149951,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616164785863,
      "path": "spans/leg=media/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616163818405,
      "path": "spans/leg=institutional/ym=2023-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786101735591555575,
      "path": "gdelt_gkg/leg=media/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 26818,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5241060,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617983153184,
      "path": "documents/leg=media/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 217,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 684261,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617054719050,
      "path": "documents/leg=institutional/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1328,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1152661,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786101796956643401,
      "path": "passages/leg=media/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 3776,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 736055,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786101796930202790,
      "path": "passages/leg=institutional/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 7615,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1162511,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099270063201625,
      "path": "embeddings/leg=media/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 201,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 171237,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786099270051685438,
      "path": "embeddings/leg=institutional/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1328,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1011794,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616169863488,
      "path": "spans/leg=media/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616168902863,
      "path": "spans/leg=institutional/ym=2023-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786122390643658438,
      "path": "gdelt_gkg/leg=media/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 33830,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6180064,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617991247515,
      "path": "documents/leg=media/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 321,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 951835,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617071049962,
      "path": "documents/leg=institutional/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1299,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1129403,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786124473444809333,
      "path": "passages/leg=media/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 5525,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1066003,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786124473409807747,
      "path": "passages/leg=institutional/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 7306,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1141822,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786126194239772633,
      "path": "embeddings/leg=media/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 284,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 244897,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786126194233648682,
      "path": "embeddings/leg=institutional/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1299,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 990443,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616175549195,
      "path": "spans/leg=media/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616174456404,
      "path": "spans/leg=institutional/ym=2023-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786202533993965369,
      "path": "gdelt_gkg/leg=media/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 25771,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4908417,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617996806125,
      "path": "documents/leg=media/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 198,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 631599,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617129422035,
      "path": "documents/leg=institutional/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 127,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 122904,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786202638438232552,
      "path": "passages/leg=media/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 3200,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 668929,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786202638415494963,
      "path": "passages/leg=institutional/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 1403,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 126910,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786134138679382106,
      "path": "embeddings/leg=media/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 182,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 157317,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786134138675301946,
      "path": "embeddings/leg=institutional/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 127,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 114066,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616179757361,
      "path": "spans/leg=media/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616178822736,
      "path": "spans/leg=institutional/ym=2023-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786141681278482112,
      "path": "gdelt_gkg/leg=media/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 36199,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6769899,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618004136369,
      "path": "documents/leg=media/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 304,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 920385,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617155071325,
      "path": "documents/leg=institutional/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1324,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1108554,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786143840332408282,
      "path": "passages/leg=media/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 5095,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1018164,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786143840299480218,
      "path": "passages/leg=institutional/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 7869,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1120147,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786144993182672802,
      "path": "embeddings/leg=media/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 286,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 246515,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786144993174327141,
      "path": "embeddings/leg=institutional/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1324,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1008750,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616184968319,
      "path": "spans/leg=media/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616184036277,
      "path": "spans/leg=institutional/ym=2023-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786187303939206108,
      "path": "gdelt_gkg/leg=media/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 35903,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 7799194,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618012613868,
      "path": "documents/leg=media/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 328,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1001704,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617183953756,
      "path": "documents/leg=institutional/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2288,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1935161,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786189927588510572,
      "path": "passages/leg=media/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 6720,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1191391,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786189927545257084,
      "path": "passages/leg=institutional/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 11758,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1930602,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786191835459628657,
      "path": "embeddings/leg=media/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 283,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 244169,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786191835452782561,
      "path": "embeddings/leg=institutional/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2288,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1713651,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616191203943,
      "path": "spans/leg=media/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616190291902,
      "path": "spans/leg=institutional/ym=2023-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786157561625504285,
      "path": "gdelt_gkg/leg=media/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 27614,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5775179,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618020120945,
      "path": "documents/leg=media/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 231,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 794520,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617202622887,
      "path": "documents/leg=institutional/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1480,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1230696,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786159315467849078,
      "path": "passages/leg=media/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 4387,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 853942,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786159315439469619,
      "path": "passages/leg=institutional/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 7691,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1233320,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786160406536278892,
      "path": "embeddings/leg=media/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 214,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 180590,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786160406529332045,
      "path": "embeddings/leg=institutional/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1480,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1123087,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616196421901,
      "path": "spans/leg=media/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616195507859,
      "path": "spans/leg=institutional/ym=2023-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786164371015217552,
      "path": "gdelt_gkg/leg=media/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 30808,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5975338,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618028226901,
      "path": "documents/leg=media/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 261,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 856636,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617217314541,
      "path": "documents/leg=institutional/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1132,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1010343,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786166098299748972,
      "path": "passages/leg=media/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 4691,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 950549,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786166098269556878,
      "path": "passages/leg=institutional/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 6468,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1025949,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786167114052253083,
      "path": "embeddings/leg=media/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 245,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 203132,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786167114044392891,
      "path": "embeddings/leg=institutional/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1132,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 868109,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616201495859,
      "path": "spans/leg=media/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616200545609,
      "path": "spans/leg=institutional/ym=2023-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786171136347732960,
      "path": "gdelt_gkg/leg=media/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 25123,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4771817,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618034704391,
      "path": "documents/leg=media/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 264,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 818555,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617233578369,
      "path": "documents/leg=institutional/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1286,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1101194,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786178208512761480,
      "path": "passages/leg=media/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 4372,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 877347,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786178208484180230,
      "path": "passages/leg=institutional/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 7338,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1106287,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786179131690522827,
      "path": "embeddings/leg=media/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 248,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 205379,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786179131682315870,
      "path": "embeddings/leg=institutional/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1286,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 980772,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616206465608,
      "path": "spans/leg=media/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616205573775,
      "path": "spans/leg=institutional/ym=2024-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786182981879991578,
      "path": "gdelt_gkg/leg=media/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 35260,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6556763,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618044101353,
      "path": "documents/leg=media/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 382,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1168637,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617261529587,
      "path": "documents/leg=institutional/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 2230,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1834184,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786185333217233051,
      "path": "passages/leg=media/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 7007,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1342992,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786185333171021002,
      "path": "passages/leg=institutional/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 11031,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1818846,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786186863140042153,
      "path": "embeddings/leg=media/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 347,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 293293,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786186863130236209,
      "path": "embeddings/leg=institutional/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 2230,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1671232,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616213117149,
      "path": "spans/leg=media/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616212080441,
      "path": "spans/leg=institutional/ym=2024-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786647580744900122,
      "path": "gdelt_gkg/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 32716,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6085869,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1784673547416013665,
      "path": "wayback_discovery/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1450,
      "schema": "doc_id: string\ncaptured_at: string\nsource: string\nurl: string\nlanguage: string\nmatched_term: string",
      "size_bytes": 141046,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618065253913,
      "path": "documents/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 738,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1951100,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617278508336,
      "path": "documents/leg=institutional/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1211,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1041333,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786649406302102829,
      "path": "passages/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 8923,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 2009083,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786649406240525949,
      "path": "passages/leg=institutional/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 6857,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1055314,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1785926968757083713,
      "path": "embeddings/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1112,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 868062,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1786651413364769175,
      "path": "embeddings/leg=institutional/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1211,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 925960,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616219715398,
      "path": "spans/leg=media/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1790872616218819773,
      "path": "spans/leg=institutional/ym=2024-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 0,
      "schema": "span_id: string\npassage_id: string\ndoc_id: string\nstart_char: int32\nend_char: int32\ntext: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\nlanguage: string\ntopic: string\ntopic_relevance: string\ndomain_relevance: string\nframe_code: string\nstance: string\nconditionality: string\ncondition_text: string\nproposition_holder: string\nspeaker_type: string\nattribution_mode: string\nconfidence_level: string\nclassification_confidence: float\nrationale: string\nalternative_frame: string\nother_summary: string\ntarget_geography: string\ninstitutional_locus: string\nfinancing_mechanism: string\nsource_language: string\ntranslation_used: bool\ncodebook_version: string\nlabel_source: string\nclassifier_version: string\nadjudicated: bool\nsource_segment_id: string\nproposition_holder_segment_id: string\nsegment_registry_version: string\nsegment_registry_hash: string\ndate: string\nladder_rung: int8\nmethod_version: string\npurpose: string\nestimand: string\nprotocol_version: string\nprotocol_hash: string\ninclusion_probability: double\nsampling_weight: double",
      "size_bytes": 7856,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791027789190102792,
      "path": "gdelt_gkg/leg=media/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 41570,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 7332812,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618081896534,
      "path": "documents/leg=media/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 597,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1739686,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617297612053,
      "path": "documents/leg=institutional/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1501,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1265410,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791033222324088002,
      "path": "passages/leg=media/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 9895,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1986375,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791033222262329333,
      "path": "passages/leg=institutional/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 8537,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1273875,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791033629174989971,
      "path": "embeddings/leg=media/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 547,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 444410,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791033629164328596,
      "path": "embeddings/leg=institutional/ym=2024-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1501,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1138224,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791038315157159860,
      "path": "gdelt_gkg/leg=media/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 35978,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6661894,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618096344146,
      "path": "documents/leg=media/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 452,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1441689,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617299063935,
      "path": "documents/leg=institutional/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 2,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 19074,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791041457559544652,
      "path": "passages/leg=media/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 8557,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1655848,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791041457504971773,
      "path": "passages/leg=institutional/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 56,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 20285,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791041528912081371,
      "path": "embeddings/leg=media/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 418,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 347030,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791041528904260424,
      "path": "embeddings/leg=institutional/ym=2024-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 2,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 4124,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791046990679486908,
      "path": "gdelt_gkg/leg=media/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 27985,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5275635,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618107946410,
      "path": "documents/leg=media/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 376,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1250252,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617299916022,
      "path": "documents/leg=institutional/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 10805,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791048951623582710,
      "path": "passages/leg=media/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 6961,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1406731,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791048951580715749,
      "path": "passages/leg=institutional/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 14,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 8518,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791049016700367969,
      "path": "embeddings/leg=media/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 354,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 298477,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791049016691335942,
      "path": "embeddings/leg=institutional/ym=2024-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 2869,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791054374163401360,
      "path": "gdelt_gkg/leg=media/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 25415,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4710706,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618118977254,
      "path": "documents/leg=media/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 394,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1215333,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617303673123,
      "path": "documents/leg=institutional/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 249,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 239292,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791059027956497554,
      "path": "passages/leg=media/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 6853,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1384798,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791059027914213057,
      "path": "passages/leg=institutional/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 2061,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 249391,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791059145154575265,
      "path": "embeddings/leg=media/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 360,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 302868,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791059145147910079,
      "path": "embeddings/leg=institutional/ym=2024-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 249,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 202752,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791066120349054374,
      "path": "gdelt_gkg/leg=media/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 17589,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3446896,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618126960210,
      "path": "documents/leg=media/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 210,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 665013,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617305828050,
      "path": "documents/leg=institutional/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 111,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 111833,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791068198405135472,
      "path": "passages/leg=media/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 3501,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 710870,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791068198383375284,
      "path": "passages/leg=institutional/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 1258,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 111462,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791068259595013649,
      "path": "embeddings/leg=media/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 198,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 169152,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791068259590905720,
      "path": "embeddings/leg=institutional/ym=2024-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 111,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 102210,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791111327527651458,
      "path": "gdelt_gkg/leg=media/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 23014,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4222903,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618135103374,
      "path": "documents/leg=media/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 303,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 988086,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617321639210,
      "path": "documents/leg=institutional/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1325,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1091502,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791113832361435750,
      "path": "passages/leg=media/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 5460,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1082719,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791113832328040782,
      "path": "passages/leg=institutional/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 7065,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1093776,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791114132890735456,
      "path": "embeddings/leg=media/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 287,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 247481,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791114132880358426,
      "path": "embeddings/leg=institutional/ym=2024-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1325,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1010091,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791119405651741435,
      "path": "gdelt_gkg/leg=media/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 24580,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4704738,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618144304793,
      "path": "documents/leg=media/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 362,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1077994,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617350302473,
      "path": "documents/leg=institutional/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2456,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1946090,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791122895474773242,
      "path": "passages/leg=media/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 6129,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1202636,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791122895434792344,
      "path": "passages/leg=institutional/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 12295,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1929404,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791123449978061684,
      "path": "embeddings/leg=media/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 331,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 280886,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791123449971456794,
      "path": "embeddings/leg=institutional/ym=2024-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2456,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1837568,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791132122257435235,
      "path": "gdelt_gkg/leg=media/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 29478,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5530131,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618156008766,
      "path": "documents/leg=media/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 491,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1402954,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617371320282,
      "path": "documents/leg=institutional/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1708,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1368910,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791136273998907443,
      "path": "passages/leg=media/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 8309,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1650912,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791136273946872778,
      "path": "passages/leg=institutional/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 8826,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1379550,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791136905384444392,
      "path": "embeddings/leg=media/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 439,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 362886,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791136905374464767,
      "path": "embeddings/leg=institutional/ym=2024-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1708,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1290831,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791140521039275686,
      "path": "gdelt_gkg/leg=media/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 23147,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4208605,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618164289223,
      "path": "documents/leg=media/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 309,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 956039,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617390111289,
      "path": "documents/leg=institutional/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1426,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1224286,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791142793346237607,
      "path": "passages/leg=media/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 5240,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1043876,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791142793313478232,
      "path": "passages/leg=institutional/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 8196,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1242351,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791143223667425559,
      "path": "embeddings/leg=media/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 292,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 251084,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791143223661631328,
      "path": "embeddings/leg=institutional/ym=2024-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1426,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1083779,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791157079687161335,
      "path": "gdelt_gkg/leg=media/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 24091,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4678548,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618173769101,
      "path": "documents/leg=media/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 377,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1173950,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617407871250,
      "path": "documents/leg=institutional/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1410,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1117797,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791165901329728316,
      "path": "passages/leg=media/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 6660,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1337211,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791165901286766433,
      "path": "passages/leg=institutional/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 8163,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1121517,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791166302685384334,
      "path": "embeddings/leg=media/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 344,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 290784,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791166302677446400,
      "path": "embeddings/leg=institutional/ym=2025-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1410,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1072277,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791170384827877670,
      "path": "gdelt_gkg/leg=media/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 35140,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 6189959,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618188130254,
      "path": "documents/leg=media/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 543,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1725060,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617427950138,
      "path": "documents/leg=institutional/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1524,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1230066,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791173382151343404,
      "path": "passages/leg=media/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 10309,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 2052982,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791173382084301652,
      "path": "passages/leg=institutional/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 8697,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1234498,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791173889116942633,
      "path": "embeddings/leg=media/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 491,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 402181,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791173889099654451,
      "path": "embeddings/leg=institutional/ym=2025-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1524,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1155986,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791178477437729770,
      "path": "gdelt_gkg/leg=media/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 54183,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 9207706,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618212851040,
      "path": "documents/leg=media/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 875,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 2641824,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617448259611,
      "path": "documents/leg=institutional/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1637,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1299421,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791183931269367422,
      "path": "passages/leg=media/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 16175,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 3160649,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791183931162840191,
      "path": "passages/leg=institutional/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 9076,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1304436,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791184481632916180,
      "path": "embeddings/leg=media/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 794,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 629613,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791184481614105512,
      "path": "embeddings/leg=institutional/ym=2025-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1637,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1238727,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791189180778746812,
      "path": "gdelt_gkg/leg=media/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 23844,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4430278,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618224720013,
      "path": "documents/leg=media/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 350,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1144686,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617569832821,
      "path": "documents/leg=institutional/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1277,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1029210,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791191270134047523,
      "path": "passages/leg=media/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 6354,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1286029,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791191270095274923,
      "path": "passages/leg=institutional/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 7875,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1039275,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791191675138767312,
      "path": "embeddings/leg=media/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 323,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 274639,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791191675132018163,
      "path": "embeddings/leg=institutional/ym=2025-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1277,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 974816,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791198481440687963,
      "path": "gdelt_gkg/leg=media/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 25757,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4752666,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618236244069,
      "path": "documents/leg=media/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 440,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1351412,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617591972469,
      "path": "documents/leg=institutional/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1804,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1467993,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791201294631621500,
      "path": "passages/leg=media/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 7874,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1570688,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791201294583059295,
      "path": "passages/leg=institutional/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 9587,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1471671,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791201838119290414,
      "path": "embeddings/leg=media/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 402,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 334628,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791201838111478323,
      "path": "embeddings/leg=institutional/ym=2025-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1804,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1360996,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791220611097267105,
      "path": "gdelt_gkg/leg=media/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 17075,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 2820119,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618243647813,
      "path": "documents/leg=media/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 266,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 818309,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617610946061,
      "path": "documents/leg=institutional/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1468,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1234339,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791221776092797975,
      "path": "passages/leg=media/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 4903,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 919670,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791221776057834266,
      "path": "passages/leg=institutional/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 9042,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1256498,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791222579071264351,
      "path": "embeddings/leg=media/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 237,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 197247,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791222579061780206,
      "path": "embeddings/leg=institutional/ym=2025-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1468,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1114852,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791246253021844780,
      "path": "gdelt_gkg/leg=media/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 27298,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 5023282,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618253908862,
      "path": "documents/leg=media/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 404,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1282525,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617630234820,
      "path": "documents/leg=institutional/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1571,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1289944,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791247662399283407,
      "path": "passages/leg=media/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 7239,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1457754,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791247662354108889,
      "path": "passages/leg=institutional/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 9640,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1297724,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791248253447367833,
      "path": "embeddings/leg=media/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 375,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 314121,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791248253439102807,
      "path": "embeddings/leg=institutional/ym=2025-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 1571,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1190354,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791255754178189057,
      "path": "gdelt_gkg/leg=media/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 22476,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4118472,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618262432528,
      "path": "documents/leg=media/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 274,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 873420,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617636655768,
      "path": "documents/leg=institutional/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 172,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 178680,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791257403516938321,
      "path": "passages/leg=media/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 5151,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 982728,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791257403483166278,
      "path": "passages/leg=institutional/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 1968,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 183946,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791257512576759286,
      "path": "embeddings/leg=media/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 247,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 204640,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791257512571586933,
      "path": "embeddings/leg=institutional/ym=2025-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 172,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 147655,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791264955467276555,
      "path": "gdelt_gkg/leg=media/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 20765,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3710749,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618270958819,
      "path": "documents/leg=media/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 307,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 932134,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617658820416,
      "path": "documents/leg=institutional/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1556,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1248797,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791267516666978614,
      "path": "passages/leg=media/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 5154,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1020860,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791267516633433884,
      "path": "passages/leg=institutional/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 9190,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1258560,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791268078863686606,
      "path": "embeddings/leg=media/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 285,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 245704,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791268078853486904,
      "path": "embeddings/leg=institutional/ym=2025-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 1556,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1179275,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791291039149051633,
      "path": "gdelt_gkg/leg=media/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 22417,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4167827,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618278932233,
      "path": "documents/leg=media/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 309,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 981783,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617692803413,
      "path": "documents/leg=institutional/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2588,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 2059072,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791292585957372049,
      "path": "passages/leg=media/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 5580,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1089477,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791292585921642532,
      "path": "passages/leg=institutional/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 12877,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 2041469,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791293350593132145,
      "path": "embeddings/leg=media/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 286,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 246534,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791293350586136067,
      "path": "embeddings/leg=institutional/ym=2025-10/part-0000.parquet",
      "row_groups": 1,
      "rows": 2588,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1933985,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791308243426041452,
      "path": "gdelt_gkg/leg=media/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 19830,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3724790,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618286925396,
      "path": "documents/leg=media/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 262,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 913413,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617717455781,
      "path": "documents/leg=institutional/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1933,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1551067,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791310271362926968,
      "path": "passages/leg=media/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 4856,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1003133,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791310271323025310,
      "path": "passages/leg=institutional/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 10458,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1555851,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791310949250721813,
      "path": "embeddings/leg=media/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 249,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 206029,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791310949244983415,
      "path": "embeddings/leg=institutional/ym=2025-11/part-0000.parquet",
      "row_groups": 1,
      "rows": 1933,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1455236,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791365337925200273,
      "path": "gdelt_gkg/leg=media/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 21070,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3989483,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618295696313,
      "path": "documents/leg=media/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 256,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 811184,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617738368840,
      "path": "documents/leg=institutional/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1564,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1411626,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791366940300338175,
      "path": "passages/leg=media/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 4462,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 874375,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791366940271052502,
      "path": "passages/leg=institutional/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 8998,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1444291,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791367966093077964,
      "path": "embeddings/leg=media/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 240,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 199560,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791367966087145525,
      "path": "embeddings/leg=institutional/ym=2025-12/part-0000.parquet",
      "row_groups": 1,
      "rows": 1564,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1185402,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791456233593936293,
      "path": "gdelt_gkg/leg=media/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 20264,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3927208,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618304317313,
      "path": "documents/leg=media/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 298,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1064316,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617754058999,
      "path": "documents/leg=institutional/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1158,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1004076,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791457131301079171,
      "path": "passages/leg=media/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 5834,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1194483,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791457131264335582,
      "path": "passages/leg=institutional/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 7391,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1016779,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791457668409928173,
      "path": "embeddings/leg=media/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 278,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 226805,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791457668397430939,
      "path": "embeddings/leg=institutional/ym=2026-01/part-0000.parquet",
      "row_groups": 1,
      "rows": 1158,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 887606,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791485556192875647,
      "path": "gdelt_gkg/leg=media/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 25556,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4670595,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618314215402,
      "path": "documents/leg=media/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 333,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1085219,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617773563468,
      "path": "documents/leg=institutional/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1602,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1277842,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791487552058790505,
      "path": "passages/leg=media/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 6054,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1219365,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791487552018903503,
      "path": "passages/leg=institutional/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 9117,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1280098,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791488025855531463,
      "path": "embeddings/leg=media/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 308,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 263283,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791488025849108899,
      "path": "embeddings/leg=institutional/ym=2026-02/part-0000.parquet",
      "row_groups": 1,
      "rows": 1602,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1212842,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791499617280526443,
      "path": "gdelt_gkg/leg=media/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 26772,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4966895,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618324000533,
      "path": "documents/leg=media/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 360,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1237738,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617788042830,
      "path": "documents/leg=institutional/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1140,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 935657,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791502235130887346,
      "path": "passages/leg=media/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 6872,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1404849,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791502235088542476,
      "path": "passages/leg=institutional/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 7739,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 945447,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791502780297044781,
      "path": "embeddings/leg=media/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 337,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 285524,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791502780284457608,
      "path": "embeddings/leg=institutional/ym=2026-03/part-0000.parquet",
      "row_groups": 1,
      "rows": 1140,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 874978,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791510529700968813,
      "path": "gdelt_gkg/leg=media/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 23694,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4402978,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618333550120,
      "path": "documents/leg=media/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 352,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1154952,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617807103338,
      "path": "documents/leg=institutional/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1572,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1255719,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791512673500549016,
      "path": "passages/leg=media/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 6300,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1271963,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791512673461251646,
      "path": "passages/leg=institutional/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 8899,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1251290,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791513323969603788,
      "path": "embeddings/leg=media/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 327,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 277787,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791513323959182491,
      "path": "embeddings/leg=institutional/ym=2026-04/part-0000.parquet",
      "row_groups": 1,
      "rows": 1572,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1190846,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791520868707609836,
      "path": "gdelt_gkg/leg=media/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 23040,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4312768,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618343868045,
      "path": "documents/leg=media/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 319,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1005391,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617826765641,
      "path": "documents/leg=institutional/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1624,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1261517,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791523247749383928,
      "path": "passages/leg=media/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 5658,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1098126,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791523247713393382,
      "path": "passages/leg=institutional/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 8740,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1258339,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791523757646307033,
      "path": "embeddings/leg=media/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 294,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 252629,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791523757639157258,
      "path": "embeddings/leg=institutional/ym=2026-05/part-0000.parquet",
      "row_groups": 1,
      "rows": 1624,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1229111,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791531701484193852,
      "path": "gdelt_gkg/leg=media/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 21617,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3729368,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618353670384,
      "path": "documents/leg=media/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 321,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1022886,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617843722264,
      "path": "documents/leg=institutional/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1366,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1081991,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791534224173629615,
      "path": "passages/leg=media/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 5481,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1135222,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791534224139310150,
      "path": "passages/leg=institutional/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 8502,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1082163,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791534769076906092,
      "path": "embeddings/leg=media/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 297,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 255091,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791534769069136155,
      "path": "embeddings/leg=institutional/ym=2026-06/part-0000.parquet",
      "row_groups": 1,
      "rows": 1366,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 1040064,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423074734888089,
      "path": "gdelt_gkg/leg=media/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 28208,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4868175,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1784653861322248185,
      "path": "panel_discovery/leg=media/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 610,
      "schema": "doc_id: string\ndiscovered_at: string\npublished_at: string\nsource: string\nurl: string\nlanguage: string\nmethod: string\nmatched_term: string",
      "size_bytes": 64816,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618368836415,
      "path": "documents/leg=media/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 585,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 1685795,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617853344060,
      "path": "documents/leg=institutional/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 675,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 616876,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423572390782834,
      "path": "passages/leg=media/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 8226,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1795248,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423572340481008,
      "path": "passages/leg=institutional/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 6033,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 632830,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423674744618239,
      "path": "embeddings/leg=media/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 566,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 458926,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791637448745290359,
      "path": "embeddings/leg=institutional/ym=2026-07/part-0000.parquet",
      "row_groups": 1,
      "rows": 675,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 532358,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791635539773508693,
      "path": "gdelt_gkg/leg=media/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 17019,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 3304141,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618376413160,
      "path": "documents/leg=media/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 219,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 783274,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617857408955,
      "path": "documents/leg=institutional/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 204,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 205449,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791636864567690371,
      "path": "passages/leg=media/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 4184,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 849301,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791636864541131342,
      "path": "passages/leg=institutional/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 2338,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 208690,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791637448765334074,
      "path": "embeddings/leg=media/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 199,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 169849,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791637448750558664,
      "path": "embeddings/leg=institutional/ym=2026-08/part-0000.parquet",
      "row_groups": 1,
      "rows": 204,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 170223,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791646112447827938,
      "path": "gdelt_gkg/leg=media/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 23128,
      "schema": "doc_id: string\ngkg_record_id: string\npublished_at: string\nsource: string\nurl: string\nthemes: list<element: string>\n  child 0, element: string",
      "size_bytes": 4086252,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423618385469329,
      "path": "documents/leg=media/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 284,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 931145,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1792423617871802566,
      "path": "documents/leg=institutional/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 923,
      "schema": "doc_id: string\nlanguage: string\ndoc_type: string\nsource: string\ninstitution: string\nmember_state: string\ntitle: string\ntext: string\nurl: string\npublished_at: string\npublished_at_source: string\nnative_date: string\nfetched_at: string\ncontent_hash: string\nladder_rung: int8\nis_duplicate: bool\nduplicate_of: string\ndiscovery_source: string\ndiscovery_date: string\ndiscovery_query: string\nsnapshot_id: string\nsnapshot_captured_at: string",
      "size_bytes": 776050,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791648211651232087,
      "path": "passages/leg=media/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 4931,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 1019530,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791648211620119233,
      "path": "passages/leg=institutional/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 6678,
      "schema": "passage_id: string\ndoc_id: string\nseq: int32\nstart_char: int32\nend_char: int32\ntext: string\nlanguage: string\nspeaker_or_author: string\nis_quoted: bool\nattributed_to: string\ntopic_id: string\ntopic_relevance: string\nrelevance_score: float\nmatched_seed_term: string",
      "size_bytes": 786865,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791648510822663723,
      "path": "embeddings/leg=media/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 267,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 219052,
      "state": "footer_readable"
    },
    {
      "mtime_ns": 1791648510816661202,
      "path": "embeddings/leg=institutional/ym=2026-09/part-0000.parquet",
      "row_groups": 1,
      "rows": 923,
      "schema": "doc_id: string\nmodel_version: string\nembedding: list<element: halffloat>\n  child 0, element: halffloat",
      "size_bytes": 715049,
      "state": "footer_readable"
    }
  ],
  "input_inventory_sha256": "e9be135763f8eb1488be6fc98bb142d663280a7443b733c556e1605bfa002566",
  "limitations": [
    "Rows are not deduplicated documents or verified non-empty extracted text.",
    "Readable footers do not verify data pages, raw blobs, URLs, source completeness or text integrity.",
    "Checkpoint state is recorded only; candidate-set freshness and fetch success are not revalidated.",
    "Absent partitions and zero outputs are disclosed; no claim of complete acquisition is made.",
    "Embedding and passage rows have different units; their count difference is not a processing backlog.",
    "Evaluation-period metadata is operational inventory only; no model design, fitting or evaluation is performed.",
    "File inventory fingerprints cover metadata and file stats, not full-file content hashes."
  ],
  "method": "Parquet footer row counts only; no observation text, vectors, labels or evaluation results read.",
  "monthly": [
    {
      "checkpoint_state": "184/184 recorded chunks",
      "counts": {
        "documents_institutional": 1275,
        "documents_media": 265,
        "embeddings_institutional": 1275,
        "embeddings_media": 226,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 36664,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8253,
        "passages_media": 6560,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-02"
    },
    {
      "checkpoint_state": "282/282 recorded chunks",
      "counts": {
        "documents_institutional": 1833,
        "documents_media": 357,
        "embeddings_institutional": 1833,
        "embeddings_media": 312,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 56206,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 10948,
        "passages_media": 10332,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-03"
    },
    {
      "checkpoint_state": "177/177 recorded chunks",
      "counts": {
        "documents_institutional": 1205,
        "documents_media": 291,
        "embeddings_institutional": 1205,
        "embeddings_media": 243,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35358,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 6638,
        "passages_media": 10693,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-04"
    },
    {
      "checkpoint_state": "141/141 recorded chunks",
      "counts": {
        "documents_institutional": 1623,
        "documents_media": 243,
        "embeddings_institutional": 1623,
        "embeddings_media": 189,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 28164,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8879,
        "passages_media": 8778,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-05"
    },
    {
      "checkpoint_state": "104/104 recorded chunks",
      "counts": {
        "documents_institutional": 1494,
        "documents_media": 169,
        "embeddings_institutional": 1494,
        "embeddings_media": 148,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 20756,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8265,
        "passages_media": 4731,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-06"
    },
    {
      "checkpoint_state": "100/100 recorded chunks",
      "counts": {
        "documents_institutional": 1269,
        "documents_media": 157,
        "embeddings_institutional": 1269,
        "embeddings_media": 144,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 19859,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7398,
        "passages_media": 3201,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-07"
    },
    {
      "checkpoint_state": "95/95 recorded chunks",
      "counts": {
        "documents_institutional": 131,
        "documents_media": 151,
        "embeddings_institutional": 131,
        "embeddings_media": 135,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 18979,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 1325,
        "passages_media": 3012,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-08"
    },
    {
      "checkpoint_state": "103/103 recorded chunks",
      "counts": {
        "documents_institutional": 1243,
        "documents_media": 159,
        "embeddings_institutional": 1243,
        "embeddings_media": 137,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 20425,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7089,
        "passages_media": 2873,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-09"
    },
    {
      "checkpoint_state": "122/122 recorded chunks",
      "counts": {
        "documents_institutional": 2207,
        "documents_media": 179,
        "embeddings_institutional": 2207,
        "embeddings_media": 164,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 24377,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 10694,
        "passages_media": 3608,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-10"
    },
    {
      "checkpoint_state": "89/89 recorded chunks",
      "counts": {
        "documents_institutional": 1663,
        "documents_media": 124,
        "embeddings_institutional": 1663,
        "embeddings_media": 123,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 17770,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9117,
        "passages_media": 2771,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-11"
    },
    {
      "checkpoint_state": "116/116 recorded chunks",
      "counts": {
        "documents_institutional": 1258,
        "documents_media": 129,
        "embeddings_institutional": 1258,
        "embeddings_media": 120,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23019,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 6732,
        "passages_media": 2595,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2022-12"
    },
    {
      "checkpoint_state": "109/109 recorded chunks",
      "counts": {
        "documents_institutional": 1248,
        "documents_media": 174,
        "embeddings_institutional": 1248,
        "embeddings_media": 165,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 21673,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7154,
        "passages_media": 3361,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-01"
    },
    {
      "checkpoint_state": "128/128 recorded chunks",
      "counts": {
        "documents_institutional": 1527,
        "documents_media": 241,
        "embeddings_institutional": 1527,
        "embeddings_media": 212,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25533,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8613,
        "passages_media": 5318,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-02"
    },
    {
      "checkpoint_state": "137/137 recorded chunks",
      "counts": {
        "documents_institutional": 1791,
        "documents_media": 271,
        "embeddings_institutional": 1791,
        "embeddings_media": 246,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 27496,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 10135,
        "passages_media": 5102,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-03"
    },
    {
      "checkpoint_state": "142/142 recorded chunks",
      "counts": {
        "documents_institutional": 1287,
        "documents_media": 265,
        "embeddings_institutional": 1287,
        "embeddings_media": 230,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 28301,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7181,
        "passages_media": 4711,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-04"
    },
    {
      "checkpoint_state": "178/178 recorded chunks",
      "counts": {
        "documents_institutional": 1517,
        "documents_media": 284,
        "embeddings_institutional": 1517,
        "embeddings_media": 248,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35437,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8478,
        "passages_media": 5886,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-05"
    },
    {
      "checkpoint_state": "135/135 recorded chunks",
      "counts": {
        "documents_institutional": 1328,
        "documents_media": 217,
        "embeddings_institutional": 1328,
        "embeddings_media": 201,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 26818,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7615,
        "passages_media": 3776,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-06"
    },
    {
      "checkpoint_state": "170/170 recorded chunks",
      "counts": {
        "documents_institutional": 1299,
        "documents_media": 321,
        "embeddings_institutional": 1299,
        "embeddings_media": 284,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 33830,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7306,
        "passages_media": 5525,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-07"
    },
    {
      "checkpoint_state": "129/129 recorded chunks",
      "counts": {
        "documents_institutional": 127,
        "documents_media": 198,
        "embeddings_institutional": 127,
        "embeddings_media": 182,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25771,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 1403,
        "passages_media": 3200,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-08"
    },
    {
      "checkpoint_state": "181/181 recorded chunks",
      "counts": {
        "documents_institutional": 1324,
        "documents_media": 304,
        "embeddings_institutional": 1324,
        "embeddings_media": 286,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 36199,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7869,
        "passages_media": 5095,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-09"
    },
    {
      "checkpoint_state": "180/180 recorded chunks",
      "counts": {
        "documents_institutional": 2288,
        "documents_media": 328,
        "embeddings_institutional": 2288,
        "embeddings_media": 283,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35903,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 11758,
        "passages_media": 6720,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-10"
    },
    {
      "checkpoint_state": "139/139 recorded chunks",
      "counts": {
        "documents_institutional": 1480,
        "documents_media": 231,
        "embeddings_institutional": 1480,
        "embeddings_media": 214,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 27614,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7691,
        "passages_media": 4387,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-11"
    },
    {
      "checkpoint_state": "155/155 recorded chunks",
      "counts": {
        "documents_institutional": 1132,
        "documents_media": 261,
        "embeddings_institutional": 1132,
        "embeddings_media": 245,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 30808,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 6468,
        "passages_media": 4691,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2023-12"
    },
    {
      "checkpoint_state": "126/126 recorded chunks",
      "counts": {
        "documents_institutional": 1286,
        "documents_media": 264,
        "embeddings_institutional": 1286,
        "embeddings_media": 248,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25123,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7338,
        "passages_media": 4372,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2024-01"
    },
    {
      "checkpoint_state": "177/177 recorded chunks",
      "counts": {
        "documents_institutional": 2230,
        "documents_media": 382,
        "embeddings_institutional": 2230,
        "embeddings_media": 347,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35260,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 11031,
        "passages_media": 7007,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [],
      "ym": "2024-02"
    },
    {
      "checkpoint_state": "171/171 recorded chunks",
      "counts": {
        "documents_institutional": 1211,
        "documents_media": 738,
        "embeddings_institutional": 1211,
        "embeddings_media": 1112,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 32716,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 6857,
        "passages_media": 8923,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 1450
      },
      "gaps": [],
      "ym": "2024-03"
    },
    {
      "checkpoint_state": "208/208 recorded chunks",
      "counts": {
        "documents_institutional": 1501,
        "documents_media": 597,
        "embeddings_institutional": 1501,
        "embeddings_media": 547,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 41570,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8537,
        "passages_media": 9895,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-04"
    },
    {
      "checkpoint_state": "180/180 recorded chunks",
      "counts": {
        "documents_institutional": 2,
        "documents_media": 452,
        "embeddings_institutional": 2,
        "embeddings_media": 418,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35978,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 56,
        "passages_media": 8557,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-05"
    },
    {
      "checkpoint_state": "140/140 recorded chunks",
      "counts": {
        "documents_institutional": 1,
        "documents_media": 376,
        "embeddings_institutional": 1,
        "embeddings_media": 354,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 27985,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 14,
        "passages_media": 6961,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-06"
    },
    {
      "checkpoint_state": "128/128 recorded chunks",
      "counts": {
        "documents_institutional": 249,
        "documents_media": 394,
        "embeddings_institutional": 249,
        "embeddings_media": 360,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25415,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 2061,
        "passages_media": 6853,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-07"
    },
    {
      "checkpoint_state": "88/88 recorded chunks",
      "counts": {
        "documents_institutional": 111,
        "documents_media": 210,
        "embeddings_institutional": 111,
        "embeddings_media": 198,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 17589,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 1258,
        "passages_media": 3501,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-08"
    },
    {
      "checkpoint_state": "116/116 recorded chunks",
      "counts": {
        "documents_institutional": 1325,
        "documents_media": 303,
        "embeddings_institutional": 1325,
        "embeddings_media": 287,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23014,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7065,
        "passages_media": 5460,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-09"
    },
    {
      "checkpoint_state": "123/123 recorded chunks",
      "counts": {
        "documents_institutional": 2456,
        "documents_media": 362,
        "embeddings_institutional": 2456,
        "embeddings_media": 331,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 24580,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 12295,
        "passages_media": 6129,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-10"
    },
    {
      "checkpoint_state": "148/148 recorded chunks",
      "counts": {
        "documents_institutional": 1708,
        "documents_media": 491,
        "embeddings_institutional": 1708,
        "embeddings_media": 439,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 29478,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8826,
        "passages_media": 8309,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-11"
    },
    {
      "checkpoint_state": "116/116 recorded chunks",
      "counts": {
        "documents_institutional": 1426,
        "documents_media": 309,
        "embeddings_institutional": 1426,
        "embeddings_media": 292,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23147,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8196,
        "passages_media": 5240,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2024-12"
    },
    {
      "checkpoint_state": "121/121 recorded chunks",
      "counts": {
        "documents_institutional": 1410,
        "documents_media": 377,
        "embeddings_institutional": 1410,
        "embeddings_media": 344,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 24091,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8163,
        "passages_media": 6660,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-01"
    },
    {
      "checkpoint_state": "176/176 recorded chunks",
      "counts": {
        "documents_institutional": 1524,
        "documents_media": 543,
        "embeddings_institutional": 1524,
        "embeddings_media": 491,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 35140,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8697,
        "passages_media": 10309,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-02"
    },
    {
      "checkpoint_state": "271/271 recorded chunks",
      "counts": {
        "documents_institutional": 1637,
        "documents_media": 875,
        "embeddings_institutional": 1637,
        "embeddings_media": 794,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 54183,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9076,
        "passages_media": 16175,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-03"
    },
    {
      "checkpoint_state": "120/120 recorded chunks",
      "counts": {
        "documents_institutional": 1277,
        "documents_media": 350,
        "embeddings_institutional": 1277,
        "embeddings_media": 323,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23844,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7875,
        "passages_media": 6354,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-04"
    },
    {
      "checkpoint_state": "129/129 recorded chunks",
      "counts": {
        "documents_institutional": 1804,
        "documents_media": 440,
        "embeddings_institutional": 1804,
        "embeddings_media": 402,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25757,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9587,
        "passages_media": 7874,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-05"
    },
    {
      "checkpoint_state": "86/86 recorded chunks",
      "counts": {
        "documents_institutional": 1468,
        "documents_media": 266,
        "embeddings_institutional": 1468,
        "embeddings_media": 237,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 17075,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9042,
        "passages_media": 4903,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-06"
    },
    {
      "checkpoint_state": "137/137 recorded chunks",
      "counts": {
        "documents_institutional": 1571,
        "documents_media": 404,
        "embeddings_institutional": 1571,
        "embeddings_media": 375,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 27298,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9640,
        "passages_media": 7239,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-07"
    },
    {
      "checkpoint_state": "113/113 recorded chunks",
      "counts": {
        "documents_institutional": 172,
        "documents_media": 274,
        "embeddings_institutional": 172,
        "embeddings_media": 247,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 22476,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 1968,
        "passages_media": 5151,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-08"
    },
    {
      "checkpoint_state": "104/104 recorded chunks",
      "counts": {
        "documents_institutional": 1556,
        "documents_media": 307,
        "embeddings_institutional": 1556,
        "embeddings_media": 285,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 20765,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9190,
        "passages_media": 5154,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-09"
    },
    {
      "checkpoint_state": "113/113 recorded chunks",
      "counts": {
        "documents_institutional": 2588,
        "documents_media": 309,
        "embeddings_institutional": 2588,
        "embeddings_media": 286,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 22417,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 12877,
        "passages_media": 5580,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-10"
    },
    {
      "checkpoint_state": "100/100 recorded chunks",
      "counts": {
        "documents_institutional": 1933,
        "documents_media": 262,
        "embeddings_institutional": 1933,
        "embeddings_media": 249,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 19830,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 10458,
        "passages_media": 4856,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-11"
    },
    {
      "checkpoint_state": "106/106 recorded chunks",
      "counts": {
        "documents_institutional": 1564,
        "documents_media": 256,
        "embeddings_institutional": 1564,
        "embeddings_media": 240,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 21070,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8998,
        "passages_media": 4462,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2025-12"
    },
    {
      "checkpoint_state": "102/102 recorded chunks",
      "counts": {
        "documents_institutional": 1158,
        "documents_media": 298,
        "embeddings_institutional": 1158,
        "embeddings_media": 278,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 20264,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7391,
        "passages_media": 5834,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-01"
    },
    {
      "checkpoint_state": "128/128 recorded chunks",
      "counts": {
        "documents_institutional": 1602,
        "documents_media": 333,
        "embeddings_institutional": 1602,
        "embeddings_media": 308,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 25556,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 9117,
        "passages_media": 6054,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-02"
    },
    {
      "checkpoint_state": "134/134 recorded chunks",
      "counts": {
        "documents_institutional": 1140,
        "documents_media": 360,
        "embeddings_institutional": 1140,
        "embeddings_media": 337,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 26772,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 7739,
        "passages_media": 6872,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-03"
    },
    {
      "checkpoint_state": "119/119 recorded chunks",
      "counts": {
        "documents_institutional": 1572,
        "documents_media": 352,
        "embeddings_institutional": 1572,
        "embeddings_media": 327,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23694,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8899,
        "passages_media": 6300,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-04"
    },
    {
      "checkpoint_state": "116/116 recorded chunks",
      "counts": {
        "documents_institutional": 1624,
        "documents_media": 319,
        "embeddings_institutional": 1624,
        "embeddings_media": 294,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23040,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8740,
        "passages_media": 5658,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-05"
    },
    {
      "checkpoint_state": "109/109 recorded chunks",
      "counts": {
        "documents_institutional": 1366,
        "documents_media": 321,
        "embeddings_institutional": 1366,
        "embeddings_media": 297,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 21617,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 8502,
        "passages_media": 5481,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-06"
    },
    {
      "checkpoint_state": "145/145 recorded chunks",
      "counts": {
        "documents_institutional": 675,
        "documents_media": 585,
        "embeddings_institutional": 675,
        "embeddings_media": 566,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 28208,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 610,
        "passages_institutional": 6033,
        "passages_media": 8226,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-07"
    },
    {
      "checkpoint_state": "86/86 recorded chunks",
      "counts": {
        "documents_institutional": 204,
        "documents_media": 219,
        "embeddings_institutional": 204,
        "embeddings_media": 199,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 17019,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 2338,
        "passages_media": 4184,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-08"
    },
    {
      "checkpoint_state": "116/116 recorded chunks",
      "counts": {
        "documents_institutional": 923,
        "documents_media": 284,
        "embeddings_institutional": 923,
        "embeddings_media": 267,
        "gdelt_gkg_institutional": 0,
        "gdelt_gkg_media": 23128,
        "panel_discovery_institutional": 0,
        "panel_discovery_media": 0,
        "passages_institutional": 6678,
        "passages_media": 4931,
        "spans_institutional": 0,
        "spans_media": 0,
        "wayback_discovery_institutional": 0,
        "wayback_discovery_media": 0
      },
      "gaps": [
        "spans_media:partition_absent",
        "spans_institutional:partition_absent"
      ],
      "ym": "2026-09"
    }
  ],
  "publication_authorized": false,
  "totals": {
    "documents_institutional": 73823,
    "documents_media": 17931,
    "embeddings_institutional": 73823,
    "embeddings_media": 16816,
    "gdelt_gkg_institutional": 0,
    "gdelt_gkg_media": 1522059,
    "panel_discovery_institutional": 0,
    "panel_discovery_media": 610,
    "passages_institutional": 421551,
    "passages_media": 336390,
    "spans_institutional": 0,
    "spans_media": 0,
    "wayback_discovery_institutional": 0,
    "wayback_discovery_media": 1450
  },
  "window": [
    "2022-02",
    "2026-09"
  ]
}
