{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3THLWO42K5BWKKCITOR4VRKBDA","short_pith_number":"pith:3THLWO42","schema_version":"1.0","canonical_sha256":"dccebb3b9a57436528489ba3cac541181473f69d30944806846d0ca1894eab86","source":{"kind":"arxiv","id":"2506.06371","version":2},"attestation_state":"computed","paper":{"title":"Relationship Detection on Tabular Data Using Statistical Analysis and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christos Panagiotopoulos, Georgios Th. Papadopoulos, Panagiotis Koletsis, Vasilis Efthymiou","submitted_at":"2025-06-04T12:11:05Z","abstract_excerpt":"Over the past few years, table interpretation tasks have made significant progress due to their importance and the introduction of new technologies and benchmarks in the field. This work experiments with a hybrid approach for detecting relationships among columns of unlabeled tabular data, using a Knowledge Graph (KG) as a reference point, a task known as CPA. This approach leverages large language models (LLMs) while employing statistical analysis to reduce the search space of potential KG relations. The main modules of this approach for reducing the search space are domain and range constrai"},"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":"2506.06371","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T12:11:05Z","cross_cats_sorted":[],"title_canon_sha256":"2504cbdcfb6c7a24e64d6d5575b78cf186127c968291d634b3b3a5a1f4d28ef4","abstract_canon_sha256":"773860db0c4205e8d7b6092abf77f3e20e346e1d3921be4b220f7a6b759d4511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:31.108009Z","signature_b64":"QzHwWFT9IP/xhT6Zj+f7w+7UjY4bclyszaDe7efngjNwtMJjsS56zjIrP2cfMGjQhk4OvQWtMUt/cRThy0ZACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dccebb3b9a57436528489ba3cac541181473f69d30944806846d0ca1894eab86","last_reissued_at":"2026-07-05T11:54:31.107530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:31.107530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relationship Detection on Tabular Data Using Statistical Analysis and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christos Panagiotopoulos, Georgios Th. Papadopoulos, Panagiotis Koletsis, Vasilis Efthymiou","submitted_at":"2025-06-04T12:11:05Z","abstract_excerpt":"Over the past few years, table interpretation tasks have made significant progress due to their importance and the introduction of new technologies and benchmarks in the field. This work experiments with a hybrid approach for detecting relationships among columns of unlabeled tabular data, using a Knowledge Graph (KG) as a reference point, a task known as CPA. This approach leverages large language models (LLMs) while employing statistical analysis to reduce the search space of potential KG relations. The main modules of this approach for reducing the search space are domain and range constrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06371","kind":"arxiv","version":2},"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/2506.06371/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":"2506.06371","created_at":"2026-07-05T11:54:31.107584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06371v2","created_at":"2026-07-05T11:54:31.107584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06371","created_at":"2026-07-05T11:54:31.107584+00:00"},{"alias_kind":"pith_short_12","alias_value":"3THLWO42K5BW","created_at":"2026-07-05T11:54:31.107584+00:00"},{"alias_kind":"pith_short_16","alias_value":"3THLWO42K5BWKKCI","created_at":"2026-07-05T11:54:31.107584+00:00"},{"alias_kind":"pith_short_8","alias_value":"3THLWO42","created_at":"2026-07-05T11:54:31.107584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.11548","citing_title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA","json":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA.json","graph_json":"https://pith.science/api/pith-number/3THLWO42K5BWKKCITOR4VRKBDA/graph.json","events_json":"https://pith.science/api/pith-number/3THLWO42K5BWKKCITOR4VRKBDA/events.json","paper":"https://pith.science/paper/3THLWO42"},"agent_actions":{"view_html":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA","download_json":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA.json","view_paper":"https://pith.science/paper/3THLWO42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06371&json=true","fetch_graph":"https://pith.science/api/pith-number/3THLWO42K5BWKKCITOR4VRKBDA/graph.json","fetch_events":"https://pith.science/api/pith-number/3THLWO42K5BWKKCITOR4VRKBDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA/action/storage_attestation","attest_author":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA/action/author_attestation","sign_citation":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA/action/citation_signature","submit_replication":"https://pith.science/pith/3THLWO42K5BWKKCITOR4VRKBDA/action/replication_record"}},"created_at":"2026-07-05T11:54:31.107584+00:00","updated_at":"2026-07-05T11:54:31.107584+00:00"}