{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CM2B5KC3DMLRN6W53QZWF7UN7Z","short_pith_number":"pith:CM2B5KC3","canonical_record":{"source":{"id":"2503.21810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-25T16:26:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"cbc5655f9eadec5c7dcd7f7f48e5199ba58f7de139d55372e289eb5ca5e22154","abstract_canon_sha256":"782081f336eb8ad074c5640af77d423ab2d0fb94b99e0bf65d748ca4357f22be"},"schema_version":"1.0"},"canonical_sha256":"13341ea85b1b1716fadddc3362fe8dfe59aea38a1c991d509965db8a3497505a","source":{"kind":"arxiv","id":"2503.21810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21810","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21810v1","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21810","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"CM2B5KC3DMLR","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"CM2B5KC3DMLRN6W5","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"CM2B5KC3","created_at":"2026-07-05T10:41:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CM2B5KC3DMLRN6W53QZWF7UN7Z","target":"record","payload":{"canonical_record":{"source":{"id":"2503.21810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-25T16:26:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"cbc5655f9eadec5c7dcd7f7f48e5199ba58f7de139d55372e289eb5ca5e22154","abstract_canon_sha256":"782081f336eb8ad074c5640af77d423ab2d0fb94b99e0bf65d748ca4357f22be"},"schema_version":"1.0"},"canonical_sha256":"13341ea85b1b1716fadddc3362fe8dfe59aea38a1c991d509965db8a3497505a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:02.593963Z","signature_b64":"cawQL8V34DZvLoF0Vg9pxBpW/1uYfBJf8EZcd36P8cNzaAl8XuFpo5ATyF7dn8x/Hq7yB4b4WpWLJnv784GhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13341ea85b1b1716fadddc3362fe8dfe59aea38a1c991d509965db8a3497505a","last_reissued_at":"2026-07-05T10:41:02.593484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:02.593484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.21810","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTBGXddl1ERxHnY9NMOp/DJBCI3Z5YvrI7xBvH220ZnQ4mK7PlacqJtmaRUq4cRF+qVO0mrUraPjbIeTFSVjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:16:11.452299Z"},"content_sha256":"1968e0b524bc76df90b9be83972a9462b83dcbc6275ebedb10c2d966a89d5822","schema_version":"1.0","event_id":"sha256:1968e0b524bc76df90b9be83972a9462b83dcbc6275ebedb10c2d966a89d5822"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CM2B5KC3DMLRN6W53QZWF7UN7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taxonomy Inference for Tabular Data Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.DB","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","submitted_at":"2025-03-25T16:26:05Z","abstract_excerpt":"Taxonomy inference for tabular data is a critical task of schema inference, aiming at discovering entity types (i.e., concepts) of the tables and building their hierarchy. It can play an important role in data management, data exploration, ontology learning, and many data-centric applications. Existing schema inference systems focus more on XML, JSON or RDF data, and often rely on lexical formats and structures of the data for calculating similarities, with limited exploitation of the semantics of the text across a table. Motivated by recent works on taxonomy completion and construction using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21810","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/2503.21810/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":"2026-07-05T10:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXgvsLB47G1oU0Jm6NIK3hzz/pDGGb7JNCegFrQ/fIZl7dTvDUemqsaGoP34Y96+dxXf2Zw8UHi67Ace/ZM0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:16:11.453292Z"},"content_sha256":"4939b684f7f7d57f35b0cc22c1ced3a28f6fe65d6c0882d3933fa6fc86910848","schema_version":"1.0","event_id":"sha256:4939b684f7f7d57f35b0cc22c1ced3a28f6fe65d6c0882d3933fa6fc86910848"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/bundle.json","state_url":"https://pith.science/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/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":"2026-08-19T12:16:11Z","links":{"resolver":"https://pith.science/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z","bundle":"https://pith.science/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/bundle.json","state":"https://pith.science/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CM2B5KC3DMLRN6W53QZWF7UN7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CM2B5KC3DMLRN6W53QZWF7UN7Z","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":"782081f336eb8ad074c5640af77d423ab2d0fb94b99e0bf65d748ca4357f22be","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-25T16:26:05Z","title_canon_sha256":"cbc5655f9eadec5c7dcd7f7f48e5199ba58f7de139d55372e289eb5ca5e22154"},"schema_version":"1.0","source":{"id":"2503.21810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21810","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21810v1","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21810","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"CM2B5KC3DMLR","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"CM2B5KC3DMLRN6W5","created_at":"2026-07-05T10:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"CM2B5KC3","created_at":"2026-07-05T10:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:4939b684f7f7d57f35b0cc22c1ced3a28f6fe65d6c0882d3933fa6fc86910848","target":"graph","created_at":"2026-07-05T10:41:02Z","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/2503.21810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Taxonomy inference for tabular data is a critical task of schema inference, aiming at discovering entity types (i.e., concepts) of the tables and building their hierarchy. It can play an important role in data management, data exploration, ontology learning, and many data-centric applications. Existing schema inference systems focus more on XML, JSON or RDF data, and often rely on lexical formats and structures of the data for calculating similarities, with limited exploitation of the semantics of the text across a table. Motivated by recent works on taxonomy completion and construction using ","authors_text":"Jiaoyan Chen, Norman W. Paton, Zhenyu Wu","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-25T16:26:05Z","title":"Taxonomy Inference for Tabular Data Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21810","kind":"arxiv","version":1},"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":"sha256:1968e0b524bc76df90b9be83972a9462b83dcbc6275ebedb10c2d966a89d5822","target":"record","created_at":"2026-07-05T10:41:02Z","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":"782081f336eb8ad074c5640af77d423ab2d0fb94b99e0bf65d748ca4357f22be","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-25T16:26:05Z","title_canon_sha256":"cbc5655f9eadec5c7dcd7f7f48e5199ba58f7de139d55372e289eb5ca5e22154"},"schema_version":"1.0","source":{"id":"2503.21810","kind":"arxiv","version":1}},"canonical_sha256":"13341ea85b1b1716fadddc3362fe8dfe59aea38a1c991d509965db8a3497505a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13341ea85b1b1716fadddc3362fe8dfe59aea38a1c991d509965db8a3497505a","first_computed_at":"2026-07-05T10:41:02.593484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:02.593484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cawQL8V34DZvLoF0Vg9pxBpW/1uYfBJf8EZcd36P8cNzaAl8XuFpo5ATyF7dn8x/Hq7yB4b4WpWLJnv784GhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:02.593963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1968e0b524bc76df90b9be83972a9462b83dcbc6275ebedb10c2d966a89d5822","sha256:4939b684f7f7d57f35b0cc22c1ced3a28f6fe65d6c0882d3933fa6fc86910848"],"state_sha256":"f2a2da42b3063a4d55814457cc5e4650095a02b0845155d2166f25db7b728162"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mxfI1dBHshLmk5Pr7cw6hfChVX8TDGGpvlaUsGA2hoAJ9vyLDIefikfuRvvl2GOOfW9813hJ6F9T8DXNVrphCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:16:11.460728Z","bundle_sha256":"82f314dceb0718fd392f0819f9fc128c33ac07baab0887b47b325d18fe13fe1b"}}