{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BRXMNZFQGYUGHITPF6CC7QLI6E","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":"6378c49068896a3f04b18cffeadd57a9816c7f916e167de00be2897ad11558ce","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T00:15:40Z","title_canon_sha256":"14d420ca2945dbb9feea31c64f34cfd6af196aff1411afa7c3620879b591af18"},"schema_version":"1.0","source":{"id":"2301.04770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04770","created_at":"2026-07-05T05:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04770v1","created_at":"2026-07-05T05:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04770","created_at":"2026-07-05T05:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"BRXMNZFQGYUG","created_at":"2026-07-05T05:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"BRXMNZFQGYUGHITP","created_at":"2026-07-05T05:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"BRXMNZFQ","created_at":"2026-07-05T05:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:47a95beb32bb912bdd1761becc875ac0117b234fe876d7cedf0a10c964d8438f","target":"graph","created_at":"2026-07-05T05:32:36Z","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/2301.04770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity resolution has been an essential and well-studied task in data cleaning research for decades. Existing work has discussed the feasibility of utilizing pre-trained language models to perform entity resolution and achieved promising results. However, few works have discussed injecting domain knowledge to improve the performance of pre-trained language models on entity resolution tasks. In this study, we propose Knowledge Augmented Entity Resolution (KAER), a novel framework named for augmenting pre-trained language models with external knowledge for entity resolution. We discuss the resul","authors_text":"Bertram Lud\\\"ascher, Lan Li, Liri Fang, Vetle I. Torvik, Yiren Liu","cross_cats":["cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T00:15:40Z","title":"KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04770","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:ca5e4a39171945ab16e9c4460b8ecdf034184c58ccd4ac9ed677849dadd9b353","target":"record","created_at":"2026-07-05T05:32:36Z","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":"6378c49068896a3f04b18cffeadd57a9816c7f916e167de00be2897ad11558ce","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T00:15:40Z","title_canon_sha256":"14d420ca2945dbb9feea31c64f34cfd6af196aff1411afa7c3620879b591af18"},"schema_version":"1.0","source":{"id":"2301.04770","kind":"arxiv","version":1}},"canonical_sha256":"0c6ec6e4b0362863a26f2f842fc168f1249adfcd9d67225672d67e7e4eb92057","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c6ec6e4b0362863a26f2f842fc168f1249adfcd9d67225672d67e7e4eb92057","first_computed_at":"2026-07-05T05:32:36.126389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:36.126389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZUYSue6mczb7aj27dnsqbg8pfxcGWSmHyXALZ37tOmdgzfKgivJKmd7l7Ke/Ukov35Cle+rvUFabc2iEMvuGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:36.126780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca5e4a39171945ab16e9c4460b8ecdf034184c58ccd4ac9ed677849dadd9b353","sha256:47a95beb32bb912bdd1761becc875ac0117b234fe876d7cedf0a10c964d8438f"],"state_sha256":"7ff74087e443585ceda2ecf04714941eabf0cdf2f4191ba6a82aa9c1b41421db"}