{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6B5Y4E5FCCOYQY4XZOPSIRUWK5","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":"5f44e28f7d381dab9c2602e1785002c1334c970a60e9337cefbc725310edd17c","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T08:47:50Z","title_canon_sha256":"279debee8791b8fad29288804582f93d5db8bb5a79cb284fb2dc2fde7e7167f0"},"schema_version":"1.0","source":{"id":"2402.01685","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01685","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01685v3","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01685","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"6B5Y4E5FCCOY","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"6B5Y4E5FCCOYQY4X","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"6B5Y4E5F","created_at":"2026-07-05T10:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:6b13768e6347660ef4cd99bb9c4e09d952c7526c0ebedfc6134d187b2821fa02","target":"graph","created_at":"2026-07-05T10:57:52Z","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/2402.01685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SMUTF (Schema Matching Using Generative Tags and Hybrid Features), a unique approach for large-scale tabular data schema matching (SM), which assumes that supervised learning does not affect performance in open-domain tasks, thereby enabling effective cross-domain matching. This system uniquely combines rule-based feature engineering, pre-trained language models, and generative large language models. In an innovative adaptation inspired by the Humanitarian Exchange Language, we deploy \"generative tags\" for each data column, enhancing the effectiveness of SM. SMUTF exhibits extensi","authors_text":"Chenwei Xu, Haozheng Luo, Mei Di, Richard Tzong-Han Tsai, Yu Zhang","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T08:47:50Z","title":"SMUTF: Schema Matching Using Generative Tags and Hybrid Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01685","kind":"arxiv","version":3},"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:a25a9d7c55956af7fbd707440e8bf193c1573f7679ff7beaaa3e1858a4d66114","target":"record","created_at":"2026-07-05T10:57:52Z","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":"5f44e28f7d381dab9c2602e1785002c1334c970a60e9337cefbc725310edd17c","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T08:47:50Z","title_canon_sha256":"279debee8791b8fad29288804582f93d5db8bb5a79cb284fb2dc2fde7e7167f0"},"schema_version":"1.0","source":{"id":"2402.01685","kind":"arxiv","version":3}},"canonical_sha256":"f07b8e13a5109d886397cb9f244696576bf84c16844ad26e3361ee6af48a2088","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f07b8e13a5109d886397cb9f244696576bf84c16844ad26e3361ee6af48a2088","first_computed_at":"2026-07-05T10:57:52.424361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:52.424361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LlwomgU8d+AYZMPcO5+oBxm0fjMn/XNeGrZEIlMQtea+gYkqU0OGQ3lGri7OkaANxZ2KVyoFkes7JSgSH060Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:52.424880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01685","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a25a9d7c55956af7fbd707440e8bf193c1573f7679ff7beaaa3e1858a4d66114","sha256:6b13768e6347660ef4cd99bb9c4e09d952c7526c0ebedfc6134d187b2821fa02"],"state_sha256":"4786135d8021e24dc718efd7b9e72ee9c2ff5085b4f6879fb901a0d39726a927"}