{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5GM7RMX7QA2IU6HK34EUPUUEVC","short_pith_number":"pith:5GM7RMX7","schema_version":"1.0","canonical_sha256":"e999f8b2ff80348a78eadf0947d284a88a22e490ff4e8a834a8405f984ea2c9f","source":{"kind":"arxiv","id":"2209.13589","version":1},"attestation_state":"computed","paper":{"title":"SANTOS: Relationship-based Semantic Table Union Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aamod Khatiwada, Grace Fan, Mirek Riedewald, Ren\\'ee J. Miller, Roee Shraga, Wolfgang Gatterbauer, Zixuan Chen","submitted_at":"2022-09-27T17:59:41Z","abstract_excerpt":"Existing techniques for unionable table search define unionability using metadata (tables must have the same or similar schemas) or column-based metrics (for example, the values in a table should be drawn from the same domain). In this work, we introduce the use of semantic relationships between pairs of columns in a table to improve the accuracy of union search. Consequently, we introduce a new notion of unionability that considers relationships between columns, together with the semantics of columns, in a principled way. To do so, we present two new methods to discover semantic relationship "},"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":"2209.13589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-09-27T17:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"114cccdbc3e484cfac2b405f9321a2cdf5b3fd5014af870bd991c170ed850db5","abstract_canon_sha256":"506e649004a4f9516215b2b560bcab1cadcfd9da1f7dae1951208ea6c85b1e57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:34.073201Z","signature_b64":"z7aUxB3AGVwQjRU9TDsF53DLVWZGk8X8sbGrTh6xijB9wadB6Z6T2Pj27OW1Y4VAnh4JQ1WmUQ0tnmbHLelOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e999f8b2ff80348a78eadf0947d284a88a22e490ff4e8a834a8405f984ea2c9f","last_reissued_at":"2026-07-05T05:01:34.072742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:34.072742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SANTOS: Relationship-based Semantic Table Union Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aamod Khatiwada, Grace Fan, Mirek Riedewald, Ren\\'ee J. Miller, Roee Shraga, Wolfgang Gatterbauer, Zixuan Chen","submitted_at":"2022-09-27T17:59:41Z","abstract_excerpt":"Existing techniques for unionable table search define unionability using metadata (tables must have the same or similar schemas) or column-based metrics (for example, the values in a table should be drawn from the same domain). In this work, we introduce the use of semantic relationships between pairs of columns in a table to improve the accuracy of union search. Consequently, we introduce a new notion of unionability that considers relationships between columns, together with the semantics of columns, in a principled way. To do so, we present two new methods to discover semantic relationship "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13589","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/2209.13589/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":"2209.13589","created_at":"2026-07-05T05:01:34.072799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13589v1","created_at":"2026-07-05T05:01:34.072799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13589","created_at":"2026-07-05T05:01:34.072799+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GM7RMX7QA2I","created_at":"2026-07-05T05:01:34.072799+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GM7RMX7QA2IU6HK","created_at":"2026-07-05T05:01:34.072799+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GM7RMX7","created_at":"2026-07-05T05:01:34.072799+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/5GM7RMX7QA2IU6HK34EUPUUEVC","json":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC.json","graph_json":"https://pith.science/api/pith-number/5GM7RMX7QA2IU6HK34EUPUUEVC/graph.json","events_json":"https://pith.science/api/pith-number/5GM7RMX7QA2IU6HK34EUPUUEVC/events.json","paper":"https://pith.science/paper/5GM7RMX7"},"agent_actions":{"view_html":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC","download_json":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC.json","view_paper":"https://pith.science/paper/5GM7RMX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13589&json=true","fetch_graph":"https://pith.science/api/pith-number/5GM7RMX7QA2IU6HK34EUPUUEVC/graph.json","fetch_events":"https://pith.science/api/pith-number/5GM7RMX7QA2IU6HK34EUPUUEVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC/action/storage_attestation","attest_author":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC/action/author_attestation","sign_citation":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC/action/citation_signature","submit_replication":"https://pith.science/pith/5GM7RMX7QA2IU6HK34EUPUUEVC/action/replication_record"}},"created_at":"2026-07-05T05:01:34.072799+00:00","updated_at":"2026-07-05T05:01:34.072799+00:00"}