{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HKWAAXESHTCQDV45HW76CP4FWC","short_pith_number":"pith:HKWAAXES","schema_version":"1.0","canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","source":{"kind":"arxiv","id":"2001.10112","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Schema Labels to Enhance Dataset Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Brian D. Davison, Haiyan Jia, Jeff Heflin, Zhiyu Chen","submitted_at":"2020-01-27T22:41:02Z","abstract_excerpt":"A search engine's ability to retrieve desirable datasets is important for data sharing and reuse. Existing dataset search engines typically rely on matching queries to dataset descriptions. However, a user may not have enough prior knowledge to write a query using terms that match with description text.We propose a novel schema label generation model which generates possible schema labels based on dataset table content. We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity betw"},"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":"2001.10112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16583c4253deac2e733a1ad4bb079898dcb46f46b85d26cd764fcd4ccaa1f5bf","abstract_canon_sha256":"ea22ac5a0e9791d5325d6fbefcf57c4703cd7f885d7318a47c2084643f8baa38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:36:49.908039Z","signature_b64":"tp+YR04C/cvwAU19UfRs07VRPuo2AJGn4YvX9XyJimAa0tY2Ms+xPzbcO1Xf92AR/cxT0ww9dBg0H78DhZuBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","last_reissued_at":"2026-07-05T00:36:49.907638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:36:49.907638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Schema Labels to Enhance Dataset Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Brian D. Davison, Haiyan Jia, Jeff Heflin, Zhiyu Chen","submitted_at":"2020-01-27T22:41:02Z","abstract_excerpt":"A search engine's ability to retrieve desirable datasets is important for data sharing and reuse. Existing dataset search engines typically rely on matching queries to dataset descriptions. However, a user may not have enough prior knowledge to write a query using terms that match with description text.We propose a novel schema label generation model which generates possible schema labels based on dataset table content. We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10112","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/2001.10112/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":"2001.10112","created_at":"2026-07-05T00:36:49.907696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.10112v1","created_at":"2026-07-05T00:36:49.907696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10112","created_at":"2026-07-05T00:36:49.907696+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKWAAXESHTCQ","created_at":"2026-07-05T00:36:49.907696+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKWAAXESHTCQDV45","created_at":"2026-07-05T00:36:49.907696+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKWAAXES","created_at":"2026-07-05T00:36:49.907696+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/HKWAAXESHTCQDV45HW76CP4FWC","json":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC.json","graph_json":"https://pith.science/api/pith-number/HKWAAXESHTCQDV45HW76CP4FWC/graph.json","events_json":"https://pith.science/api/pith-number/HKWAAXESHTCQDV45HW76CP4FWC/events.json","paper":"https://pith.science/paper/HKWAAXES"},"agent_actions":{"view_html":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC","download_json":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC.json","view_paper":"https://pith.science/paper/HKWAAXES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.10112&json=true","fetch_graph":"https://pith.science/api/pith-number/HKWAAXESHTCQDV45HW76CP4FWC/graph.json","fetch_events":"https://pith.science/api/pith-number/HKWAAXESHTCQDV45HW76CP4FWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/action/storage_attestation","attest_author":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/action/author_attestation","sign_citation":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/action/citation_signature","submit_replication":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/action/replication_record"}},"created_at":"2026-07-05T00:36:49.907696+00:00","updated_at":"2026-07-05T00:36:49.907696+00:00"}