{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UXHA3VEZSE3CDV6ZUHWHJDYCPY","short_pith_number":"pith:UXHA3VEZ","schema_version":"1.0","canonical_sha256":"a5ce0dd499913621d7d9a1ec748f027e023e9b626f4c9d2d793768097d922c97","source":{"kind":"arxiv","id":"2605.23105","version":1},"attestation_state":"computed","paper":{"title":"Conceptual Schema Inference for Tabular Datasets using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","submitted_at":"2026-05-21T23:51:00Z","abstract_excerpt":"Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a major challenge. While prior work has primarily focused on dataset discovery and exploration, this paper addresses the complementary problem of conceptual schema inference: automatically deriving a conceptual schema that captures entity types, attributes and inter-type relationships directly from raw tables. We propose two large language model (LLM)-based ap"},"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":"2605.23105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-21T23:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"24937c24055b561d111d8eed6e6ed1aaa15a42e26fd17820040bf259cd801ce0","abstract_canon_sha256":"4df24403c30305c01e4ac600e559a62d6a4525c9a0190dff3f4cb178981de07d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:38.341144Z","signature_b64":"9IpgYqSnuT6AlPQrYm5CT2BaWzRc0hCmY9459m3z1+EKOn0k0zBYRLSpiFaA9McKxM28DbdHR4VhquYYGaOKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5ce0dd499913621d7d9a1ec748f027e023e9b626f4c9d2d793768097d922c97","last_reissued_at":"2026-05-25T02:01:38.340564Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:38.340564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conceptual Schema Inference for Tabular Datasets using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","submitted_at":"2026-05-21T23:51:00Z","abstract_excerpt":"Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a major challenge. While prior work has primarily focused on dataset discovery and exploration, this paper addresses the complementary problem of conceptual schema inference: automatically deriving a conceptual schema that captures entity types, attributes and inter-type relationships directly from raw tables. We propose two large language model (LLM)-based ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23105","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/2605.23105/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":"2605.23105","created_at":"2026-05-25T02:01:38.340648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23105v1","created_at":"2026-05-25T02:01:38.340648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23105","created_at":"2026-05-25T02:01:38.340648+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXHA3VEZSE3C","created_at":"2026-05-25T02:01:38.340648+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXHA3VEZSE3CDV6Z","created_at":"2026-05-25T02:01:38.340648+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXHA3VEZ","created_at":"2026-05-25T02:01:38.340648+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/UXHA3VEZSE3CDV6ZUHWHJDYCPY","json":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY.json","graph_json":"https://pith.science/api/pith-number/UXHA3VEZSE3CDV6ZUHWHJDYCPY/graph.json","events_json":"https://pith.science/api/pith-number/UXHA3VEZSE3CDV6ZUHWHJDYCPY/events.json","paper":"https://pith.science/paper/UXHA3VEZ"},"agent_actions":{"view_html":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY","download_json":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY.json","view_paper":"https://pith.science/paper/UXHA3VEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23105&json=true","fetch_graph":"https://pith.science/api/pith-number/UXHA3VEZSE3CDV6ZUHWHJDYCPY/graph.json","fetch_events":"https://pith.science/api/pith-number/UXHA3VEZSE3CDV6ZUHWHJDYCPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY/action/storage_attestation","attest_author":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY/action/author_attestation","sign_citation":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY/action/citation_signature","submit_replication":"https://pith.science/pith/UXHA3VEZSE3CDV6ZUHWHJDYCPY/action/replication_record"}},"created_at":"2026-05-25T02:01:38.340648+00:00","updated_at":"2026-05-25T02:01:38.340648+00:00"}