{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6NWRSG7LGXUXPQJ6KQCCIVILKL","short_pith_number":"pith:6NWRSG7L","canonical_record":{"source":{"id":"2509.04632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-04T19:50:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24937c24055b561d111d8eed6e6ed1aaa15a42e26fd17820040bf259cd801ce0","abstract_canon_sha256":"4df24403c30305c01e4ac600e559a62d6a4525c9a0190dff3f4cb178981de07d"},"schema_version":"1.0"},"canonical_sha256":"f36d191beb35e977c13e540424550b52f6d8446c415884023c39fb4ea97d4f62","source":{"kind":"arxiv","id":"2509.04632","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04632","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04632v2","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04632","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"6NWRSG7LGXUX","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"6NWRSG7LGXUXPQJ6","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"6NWRSG7L","created_at":"2026-05-27T01:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6NWRSG7LGXUXPQJ6KQCCIVILKL","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-04T19:50:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24937c24055b561d111d8eed6e6ed1aaa15a42e26fd17820040bf259cd801ce0","abstract_canon_sha256":"4df24403c30305c01e4ac600e559a62d6a4525c9a0190dff3f4cb178981de07d"},"schema_version":"1.0"},"canonical_sha256":"f36d191beb35e977c13e540424550b52f6d8446c415884023c39fb4ea97d4f62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:50.353900Z","signature_b64":"KjDyxUWEtL3vFRd4RpXWDtxGdtGa4BpSbxIddBsM8aCktremI9u4aTwZaMqm4DzaMcSnzH+gw+JmmZ8vbfKhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f36d191beb35e977c13e540424550b52f6d8446c415884023c39fb4ea97d4f62","last_reissued_at":"2026-05-27T01:04:50.353153Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:50.353153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04632","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XtNyQ2J2GmhfxkNjHEAIgBdzSnXl0FwDy128hLw0Fb/ch0MGk4vWHsTmDw8W/2FtT944RW1uC8bAOve1GioAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:08:46.228206Z"},"content_sha256":"084f86d47296c1409c661587ef8650af7d645dc0ab6e91d59625c68b1b524651","schema_version":"1.0","event_id":"sha256:084f86d47296c1409c661587ef8650af7d645dc0ab6e91d59625c68b1b524651"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6NWRSG7LGXUXPQJ6KQCCIVILKL","target":"graph","payload":{"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":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","submitted_at":"2025-09-04T19:50:16Z","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":"2509.04632","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/2509.04632/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8dFXBzzdIRdKfWAXOPxuipbG4+GBpcpUuk+YqjpBqizF4Jwqcn7KP6pe7I9ISxA0WzBIKuHi4VsULWMmXk9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:08:46.228918Z"},"content_sha256":"36e3096a8076d88ee53d62e3b27c6515abbb4d2c1faee82f40f2933149cfc6c2","schema_version":"1.0","event_id":"sha256:36e3096a8076d88ee53d62e3b27c6515abbb4d2c1faee82f40f2933149cfc6c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/bundle.json","state_url":"https://pith.science/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T22:08:46Z","links":{"resolver":"https://pith.science/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL","bundle":"https://pith.science/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/bundle.json","state":"https://pith.science/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NWRSG7LGXUXPQJ6KQCCIVILKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6NWRSG7LGXUXPQJ6KQCCIVILKL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4df24403c30305c01e4ac600e559a62d6a4525c9a0190dff3f4cb178981de07d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-04T19:50:16Z","title_canon_sha256":"24937c24055b561d111d8eed6e6ed1aaa15a42e26fd17820040bf259cd801ce0"},"schema_version":"1.0","source":{"id":"2509.04632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04632","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04632v2","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04632","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"6NWRSG7LGXUX","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"6NWRSG7LGXUXPQJ6","created_at":"2026-05-27T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"6NWRSG7L","created_at":"2026-05-27T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:36e3096a8076d88ee53d62e3b27c6515abbb4d2c1faee82f40f2933149cfc6c2","target":"graph","created_at":"2026-05-27T01:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.04632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-04T19:50:16Z","title":"Conceptual Schema Inference for Tabular Datasets using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04632","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:084f86d47296c1409c661587ef8650af7d645dc0ab6e91d59625c68b1b524651","target":"record","created_at":"2026-05-27T01:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4df24403c30305c01e4ac600e559a62d6a4525c9a0190dff3f4cb178981de07d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-04T19:50:16Z","title_canon_sha256":"24937c24055b561d111d8eed6e6ed1aaa15a42e26fd17820040bf259cd801ce0"},"schema_version":"1.0","source":{"id":"2509.04632","kind":"arxiv","version":2}},"canonical_sha256":"f36d191beb35e977c13e540424550b52f6d8446c415884023c39fb4ea97d4f62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f36d191beb35e977c13e540424550b52f6d8446c415884023c39fb4ea97d4f62","first_computed_at":"2026-05-27T01:04:50.353153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:50.353153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjDyxUWEtL3vFRd4RpXWDtxGdtGa4BpSbxIddBsM8aCktremI9u4aTwZaMqm4DzaMcSnzH+gw+JmmZ8vbfKhBg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:50.353900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:084f86d47296c1409c661587ef8650af7d645dc0ab6e91d59625c68b1b524651","sha256:36e3096a8076d88ee53d62e3b27c6515abbb4d2c1faee82f40f2933149cfc6c2"],"state_sha256":"a9234c76cd8903a083ec4f362dbab00cb5e05aacd7372e51dd110c41f9fe763d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtBJOeSrCRppyAnEZy1yhsAXMrYO6tSEXI2z6oq9xQ2HWwm8Hna191/WR3ABjwzdJru8VIct2A9glHtIGlajAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:08:46.232683Z","bundle_sha256":"6d0102212e9e69d515d997791378c281c77895fcd64b5da746d079bceab488c7"}}