{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A36GGE63GS3OHZHHAF4LDS2UE2","short_pith_number":"pith:A36GGE63","schema_version":"1.0","canonical_sha256":"06fc6313db34b6e3e4e70178b1cb5426957d6321369d536758327140ae4c387b","source":{"kind":"arxiv","id":"2502.20945","version":1},"attestation_state":"computed","paper":{"title":"Metadata-driven Table Union Search: Leveraging Semantics for Restricted Access Data Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jacco van Ossenbruggen, Margherita Martorana, Tobias Kuhn","submitted_at":"2025-02-28T10:55:40Z","abstract_excerpt":"Over the past decade, the Table Union Search (TUS) task has aimed to identify unionable tables within data lakes to improve data integration and discovery. While numerous solutions and approaches have been introduced, they primarily rely on open data, making them not applicable to restricted access data, such as medical records or government statistics, due to privacy concerns. Restricted data can still be shared through metadata, which ensures confidentiality while supporting data reuse. This paper explores how TUS can be computed on restricted access data using metadata alone. We propose a m"},"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":"2502.20945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-28T10:55:40Z","cross_cats_sorted":[],"title_canon_sha256":"edcdd8a1a556776d3961aa0340166ccc564393d5fc7c5b00954d63989bb2a4d1","abstract_canon_sha256":"93c795bf765c929a75e068bf39d838be30ee22a85a505386ca78457d648a8e0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:42.478577Z","signature_b64":"z50V/SFF3WC9E2LHkQk30vKa3Xu/KwiXKggBnDRjaXhrhp4HPmOEESr2IFRjUzor6Y02Fatya0CCfx4or82VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06fc6313db34b6e3e4e70178b1cb5426957d6321369d536758327140ae4c387b","last_reissued_at":"2026-07-05T10:21:42.478138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:42.478138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metadata-driven Table Union Search: Leveraging Semantics for Restricted Access Data Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jacco van Ossenbruggen, Margherita Martorana, Tobias Kuhn","submitted_at":"2025-02-28T10:55:40Z","abstract_excerpt":"Over the past decade, the Table Union Search (TUS) task has aimed to identify unionable tables within data lakes to improve data integration and discovery. While numerous solutions and approaches have been introduced, they primarily rely on open data, making them not applicable to restricted access data, such as medical records or government statistics, due to privacy concerns. Restricted data can still be shared through metadata, which ensures confidentiality while supporting data reuse. This paper explores how TUS can be computed on restricted access data using metadata alone. We propose a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20945","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/2502.20945/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":"2502.20945","created_at":"2026-07-05T10:21:42.478194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20945v1","created_at":"2026-07-05T10:21:42.478194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20945","created_at":"2026-07-05T10:21:42.478194+00:00"},{"alias_kind":"pith_short_12","alias_value":"A36GGE63GS3O","created_at":"2026-07-05T10:21:42.478194+00:00"},{"alias_kind":"pith_short_16","alias_value":"A36GGE63GS3OHZHH","created_at":"2026-07-05T10:21:42.478194+00:00"},{"alias_kind":"pith_short_8","alias_value":"A36GGE63","created_at":"2026-07-05T10:21:42.478194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21329","citing_title":"Something's Fishy In The Data Lake: A Critical Re-evaluation of Table Union Search Benchmarks","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2","json":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2.json","graph_json":"https://pith.science/api/pith-number/A36GGE63GS3OHZHHAF4LDS2UE2/graph.json","events_json":"https://pith.science/api/pith-number/A36GGE63GS3OHZHHAF4LDS2UE2/events.json","paper":"https://pith.science/paper/A36GGE63"},"agent_actions":{"view_html":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2","download_json":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2.json","view_paper":"https://pith.science/paper/A36GGE63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20945&json=true","fetch_graph":"https://pith.science/api/pith-number/A36GGE63GS3OHZHHAF4LDS2UE2/graph.json","fetch_events":"https://pith.science/api/pith-number/A36GGE63GS3OHZHHAF4LDS2UE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2/action/storage_attestation","attest_author":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2/action/author_attestation","sign_citation":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2/action/citation_signature","submit_replication":"https://pith.science/pith/A36GGE63GS3OHZHHAF4LDS2UE2/action/replication_record"}},"created_at":"2026-07-05T10:21:42.478194+00:00","updated_at":"2026-07-05T10:21:42.478194+00:00"}