{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JVTJFWVA37FI5SBDAWBNA2Y4YL","short_pith_number":"pith:JVTJFWVA","schema_version":"1.0","canonical_sha256":"4d6692daa0dfca8ec8230582d06b1cc2fd0a65ca788a4f9ad76710229f7ec82a","source":{"kind":"arxiv","id":"2308.13560","version":1},"attestation_state":"computed","paper":{"title":"Open Government Data Corpus for Table Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfio Gliozzo, Gaetano Rossiello, Michael Glass, Oktie Hassanzadeh, Sugato Bagchi","submitted_at":"2023-08-24T18:33:36Z","abstract_excerpt":"Increasing amounts of structured data can provide value for research and business if the relevant data can be located. Often the data is in a data lake without a consistent schema, making locating useful data challenging. Table search is a growing research area, but existing benchmarks have been limited to displayed tables. Tables sized and formatted for display in a Wikipedia page or ArXiv paper are considerably different from data tables in both scale and style. By using metadata associated with open data from government portals, we create the first dataset to benchmark search over data tabl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.13560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-08-24T18:33:36Z","cross_cats_sorted":[],"title_canon_sha256":"3f6f17d0fa99d92e5d5ca0adff5c8a65771b90bfd03dcc15f2129c03f8e20156","abstract_canon_sha256":"28f9442fe18285988bad8b7fb72e99a96b92e852d230bfe976ce92a6529a8d6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:52.143958Z","signature_b64":"gpeV2dxRT/PCb/eC452mvJ44fO8z4sx2JzwBy3+wxTK0YJnzwUShhKEIvQHZm2wTS9FOV8QyMAdVuHcYimM0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d6692daa0dfca8ec8230582d06b1cc2fd0a65ca788a4f9ad76710229f7ec82a","last_reissued_at":"2026-07-05T06:44:52.143548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:52.143548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Government Data Corpus for Table Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfio Gliozzo, Gaetano Rossiello, Michael Glass, Oktie Hassanzadeh, Sugato Bagchi","submitted_at":"2023-08-24T18:33:36Z","abstract_excerpt":"Increasing amounts of structured data can provide value for research and business if the relevant data can be located. Often the data is in a data lake without a consistent schema, making locating useful data challenging. Table search is a growing research area, but existing benchmarks have been limited to displayed tables. Tables sized and formatted for display in a Wikipedia page or ArXiv paper are considerably different from data tables in both scale and style. By using metadata associated with open data from government portals, we create the first dataset to benchmark search over data tabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13560","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.13560/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.13560","created_at":"2026-07-05T06:44:52.143605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13560v1","created_at":"2026-07-05T06:44:52.143605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13560","created_at":"2026-07-05T06:44:52.143605+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVTJFWVA37FI","created_at":"2026-07-05T06:44:52.143605+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVTJFWVA37FI5SBD","created_at":"2026-07-05T06:44:52.143605+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVTJFWVA","created_at":"2026-07-05T06:44:52.143605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL","json":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL.json","graph_json":"https://pith.science/api/pith-number/JVTJFWVA37FI5SBDAWBNA2Y4YL/graph.json","events_json":"https://pith.science/api/pith-number/JVTJFWVA37FI5SBDAWBNA2Y4YL/events.json","paper":"https://pith.science/paper/JVTJFWVA"},"agent_actions":{"view_html":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL","download_json":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL.json","view_paper":"https://pith.science/paper/JVTJFWVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13560&json=true","fetch_graph":"https://pith.science/api/pith-number/JVTJFWVA37FI5SBDAWBNA2Y4YL/graph.json","fetch_events":"https://pith.science/api/pith-number/JVTJFWVA37FI5SBDAWBNA2Y4YL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL/action/storage_attestation","attest_author":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL/action/author_attestation","sign_citation":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL/action/citation_signature","submit_replication":"https://pith.science/pith/JVTJFWVA37FI5SBDAWBNA2Y4YL/action/replication_record"}},"created_at":"2026-07-05T06:44:52.143605+00:00","updated_at":"2026-07-05T06:44:52.143605+00:00"}