{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BRXMNZFQGYUGHITPF6CC7QLI6E","short_pith_number":"pith:BRXMNZFQ","schema_version":"1.0","canonical_sha256":"0c6ec6e4b0362863a26f2f842fc168f1249adfcd9d67225672d67e7e4eb92057","source":{"kind":"arxiv","id":"2301.04770","version":1},"attestation_state":"computed","paper":{"title":"KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bertram Lud\\\"ascher, Lan Li, Liri Fang, Vetle I. Torvik, Yiren Liu","submitted_at":"2023-01-12T00:15:40Z","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"},"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":"2301.04770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T00:15:40Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"14d420ca2945dbb9feea31c64f34cfd6af196aff1411afa7c3620879b591af18","abstract_canon_sha256":"6378c49068896a3f04b18cffeadd57a9816c7f916e167de00be2897ad11558ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:36.126780Z","signature_b64":"ZUYSue6mczb7aj27dnsqbg8pfxcGWSmHyXALZ37tOmdgzfKgivJKmd7l7Ke/Ukov35Cle+rvUFabc2iEMvuGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6ec6e4b0362863a26f2f842fc168f1249adfcd9d67225672d67e7e4eb92057","last_reissued_at":"2026-07-05T05:32:36.126389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:36.126389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bertram Lud\\\"ascher, Lan Li, Liri Fang, Vetle I. Torvik, Yiren Liu","submitted_at":"2023-01-12T00:15:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04770","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/2301.04770/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":"2301.04770","created_at":"2026-07-05T05:32:36.126445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04770v1","created_at":"2026-07-05T05:32:36.126445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04770","created_at":"2026-07-05T05:32:36.126445+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRXMNZFQGYUG","created_at":"2026-07-05T05:32:36.126445+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRXMNZFQGYUGHITP","created_at":"2026-07-05T05:32:36.126445+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRXMNZFQ","created_at":"2026-07-05T05:32:36.126445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06724","citing_title":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E","json":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E.json","graph_json":"https://pith.science/api/pith-number/BRXMNZFQGYUGHITPF6CC7QLI6E/graph.json","events_json":"https://pith.science/api/pith-number/BRXMNZFQGYUGHITPF6CC7QLI6E/events.json","paper":"https://pith.science/paper/BRXMNZFQ"},"agent_actions":{"view_html":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E","download_json":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E.json","view_paper":"https://pith.science/paper/BRXMNZFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04770&json=true","fetch_graph":"https://pith.science/api/pith-number/BRXMNZFQGYUGHITPF6CC7QLI6E/graph.json","fetch_events":"https://pith.science/api/pith-number/BRXMNZFQGYUGHITPF6CC7QLI6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E/action/storage_attestation","attest_author":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E/action/author_attestation","sign_citation":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E/action/citation_signature","submit_replication":"https://pith.science/pith/BRXMNZFQGYUGHITPF6CC7QLI6E/action/replication_record"}},"created_at":"2026-07-05T05:32:36.126445+00:00","updated_at":"2026-07-05T05:32:36.126445+00:00"}