{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6J5KFVEH5D7B3O6HLGM5F4QQWD","short_pith_number":"pith:6J5KFVEH","schema_version":"1.0","canonical_sha256":"f27aa2d487e8fe1dbbc75999d2f210b0f8d3bc93619604828fb08c4ac57fc44f","source":{"kind":"arxiv","id":"2401.03426","version":2},"attestation_state":"computed","paper":{"title":"On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Jason Zhang, Fei Hao, Huahang Li, Longyu Feng, Shuangyin Li, Yuanfeng Song","submitted_at":"2024-01-07T09:06:58Z","abstract_excerpt":"Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these probl"},"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":"2401.03426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-07T09:06:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84427906b0d8ad4c4cfb43f2f0170da7917586c264a2279d84005f1dd2988683","abstract_canon_sha256":"6370eff13e8008a335e4142853d5af85899427cc3d43c707ad0f2feac70cafc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:02.194381Z","signature_b64":"XRIr4yZIprfZw23onnu6SPbS1BmA/Dphg1eGUku/xI8D419t6DqqOTNdZ977dfHyuKEX7lOXrOWUR/VisCrDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f27aa2d487e8fe1dbbc75999d2f210b0f8d3bc93619604828fb08c4ac57fc44f","last_reissued_at":"2026-07-05T09:06:02.193823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:02.193823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Jason Zhang, Fei Hao, Huahang Li, Longyu Feng, Shuangyin Li, Yuanfeng Song","submitted_at":"2024-01-07T09:06:58Z","abstract_excerpt":"Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03426","kind":"arxiv","version":2},"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/2401.03426/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":"2401.03426","created_at":"2026-07-05T09:06:02.193887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03426v2","created_at":"2026-07-05T09:06:02.193887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03426","created_at":"2026-07-05T09:06:02.193887+00:00"},{"alias_kind":"pith_short_12","alias_value":"6J5KFVEH5D7B","created_at":"2026-07-05T09:06:02.193887+00:00"},{"alias_kind":"pith_short_16","alias_value":"6J5KFVEH5D7B3O6H","created_at":"2026-07-05T09:06:02.193887+00:00"},{"alias_kind":"pith_short_8","alias_value":"6J5KFVEH","created_at":"2026-07-05T09:06:02.193887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08096","citing_title":"Identifying unique developers in OSS projects: A family of models","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25814","citing_title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD","json":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD.json","graph_json":"https://pith.science/api/pith-number/6J5KFVEH5D7B3O6HLGM5F4QQWD/graph.json","events_json":"https://pith.science/api/pith-number/6J5KFVEH5D7B3O6HLGM5F4QQWD/events.json","paper":"https://pith.science/paper/6J5KFVEH"},"agent_actions":{"view_html":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD","download_json":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD.json","view_paper":"https://pith.science/paper/6J5KFVEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03426&json=true","fetch_graph":"https://pith.science/api/pith-number/6J5KFVEH5D7B3O6HLGM5F4QQWD/graph.json","fetch_events":"https://pith.science/api/pith-number/6J5KFVEH5D7B3O6HLGM5F4QQWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD/action/storage_attestation","attest_author":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD/action/author_attestation","sign_citation":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD/action/citation_signature","submit_replication":"https://pith.science/pith/6J5KFVEH5D7B3O6HLGM5F4QQWD/action/replication_record"}},"created_at":"2026-07-05T09:06:02.193887+00:00","updated_at":"2026-07-05T09:06:02.193887+00:00"}