{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VEUQHWLLOFWZYXRG5GS7IK2ISZ","short_pith_number":"pith:VEUQHWLL","schema_version":"1.0","canonical_sha256":"a92903d96b716d9c5e26e9a5f42b4896485ce174a536a94bc0ac5987a1a4d423","source":{"kind":"arxiv","id":"2405.16884","version":3},"attestation_state":"computed","paper":{"title":"Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Hao Wang, Hongyu Lin, Le Sun, Tianshu Wang, Xianpei Han, Xiaoyang Chen, Xuanang Chen, Zhenyu Zeng","submitted_at":"2024-05-27T07:05:27Z","abstract_excerpt":"Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary matching paradigm that ignores the global consistency among record relationships. In this paper, we investigate various methodologies for LLM-based entity matching that incorporate record interactions from different perspectives. Specifically, we comprehensively compare three representative strategies: matching, comparing, and selecting, and analyze their respec"},"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":"2405.16884","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T07:05:27Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"58178413b24536846b51561be7591d56e79e39e7181e8b30ad323fbff0516822","abstract_canon_sha256":"a6629df7fe38a7ebdd30bdcdd229d47e29847e2937718d2ca7ea1f889c77dade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:13.614817Z","signature_b64":"Z6hP/QDJ74ujwhz3Gaforz7ct1yBUuDNC6Grd/JC41pB0RwsDQl7gMPXllnGITcIoMITwBZuVoZnrKdDcHg1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92903d96b716d9c5e26e9a5f42b4896485ce174a536a94bc0ac5987a1a4d423","last_reissued_at":"2026-07-05T09:48:13.614292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:13.614292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Hao Wang, Hongyu Lin, Le Sun, Tianshu Wang, Xianpei Han, Xiaoyang Chen, Xuanang Chen, Zhenyu Zeng","submitted_at":"2024-05-27T07:05:27Z","abstract_excerpt":"Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary matching paradigm that ignores the global consistency among record relationships. In this paper, we investigate various methodologies for LLM-based entity matching that incorporate record interactions from different perspectives. Specifically, we comprehensively compare three representative strategies: matching, comparing, and selecting, and analyze their respec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16884","kind":"arxiv","version":3},"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/2405.16884/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":"2405.16884","created_at":"2026-07-05T09:48:13.614365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16884v3","created_at":"2026-07-05T09:48:13.614365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16884","created_at":"2026-07-05T09:48:13.614365+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEUQHWLLOFWZ","created_at":"2026-07-05T09:48:13.614365+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEUQHWLLOFWZYXRG","created_at":"2026-07-05T09:48:13.614365+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEUQHWLL","created_at":"2026-07-05T09:48:13.614365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29750","citing_title":"Managing Map Cardinality in Automatic Disease Classification Mapping: Balancing Precision, Recall and Coverage","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ","json":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ.json","graph_json":"https://pith.science/api/pith-number/VEUQHWLLOFWZYXRG5GS7IK2ISZ/graph.json","events_json":"https://pith.science/api/pith-number/VEUQHWLLOFWZYXRG5GS7IK2ISZ/events.json","paper":"https://pith.science/paper/VEUQHWLL"},"agent_actions":{"view_html":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ","download_json":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ.json","view_paper":"https://pith.science/paper/VEUQHWLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16884&json=true","fetch_graph":"https://pith.science/api/pith-number/VEUQHWLLOFWZYXRG5GS7IK2ISZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VEUQHWLLOFWZYXRG5GS7IK2ISZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ/action/storage_attestation","attest_author":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ/action/author_attestation","sign_citation":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ/action/citation_signature","submit_replication":"https://pith.science/pith/VEUQHWLLOFWZYXRG5GS7IK2ISZ/action/replication_record"}},"created_at":"2026-07-05T09:48:13.614365+00:00","updated_at":"2026-07-05T09:48:13.614365+00:00"}