{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SIRHCO5ZT3LDINV7HMWF7K53H","short_pith_number":"pith:5SIRHCO5","schema_version":"1.0","canonical_sha256":"ec911389ddccf6b1a1b5f9d962fd5dd9cc17127cce651ee6319edb5ae0d2c9b3","source":{"kind":"arxiv","id":"2411.10629","version":1},"attestation_state":"computed","paper":{"title":"Leveraging large language models for efficient representation learning for entity resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bi T. Foua, John R. Talburt, Vivek Gunasekaran, Xiaowei Xu, Xingqiao Wang","submitted_at":"2024-11-15T23:24:07Z","abstract_excerpt":"In this paper, the authors propose TriBERTa, a supervised entity resolution system that utilizes a pre-trained large language model and a triplet loss function to learn representations for entity matching. The system consists of two steps: first, name entity records are fed into a Sentence Bidirectional Encoder Representations from Transformers (SBERT) model to generate vector representations, which are then fine-tuned using contrastive learning based on a triplet loss function. Fine-tuned representations are used as input for entity matching tasks, and the results show that the proposed appro"},"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":"2411.10629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T23:24:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f4e917ac8ebc499065289d666ba20b3c0bcf061e494e6038259f65657414e82","abstract_canon_sha256":"c564afc688605cec84320efaf23fc4410b9814d4c9e4242262258425a6919d8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:19.499397Z","signature_b64":"XsDfiFZln9gdlYvzmJtP/tpmNzQqPuCJWL+H+sjpc84nPE8hI2f6KbDwNBVb+OT0FBRTD7xwRcWoNDOKBsz4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec911389ddccf6b1a1b5f9d962fd5dd9cc17127cce651ee6319edb5ae0d2c9b3","last_reissued_at":"2026-07-05T09:36:19.498831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:19.498831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging large language models for efficient representation learning for entity resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bi T. Foua, John R. Talburt, Vivek Gunasekaran, Xiaowei Xu, Xingqiao Wang","submitted_at":"2024-11-15T23:24:07Z","abstract_excerpt":"In this paper, the authors propose TriBERTa, a supervised entity resolution system that utilizes a pre-trained large language model and a triplet loss function to learn representations for entity matching. The system consists of two steps: first, name entity records are fed into a Sentence Bidirectional Encoder Representations from Transformers (SBERT) model to generate vector representations, which are then fine-tuned using contrastive learning based on a triplet loss function. Fine-tuned representations are used as input for entity matching tasks, and the results show that the proposed appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10629","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/2411.10629/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":"2411.10629","created_at":"2026-07-05T09:36:19.498904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10629v1","created_at":"2026-07-05T09:36:19.498904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10629","created_at":"2026-07-05T09:36:19.498904+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SIRHCO5ZT3L","created_at":"2026-07-05T09:36:19.498904+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SIRHCO5ZT3LDINV","created_at":"2026-07-05T09:36:19.498904+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SIRHCO5","created_at":"2026-07-05T09:36:19.498904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H","json":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H.json","graph_json":"https://pith.science/api/pith-number/5SIRHCO5ZT3LDINV7HMWF7K53H/graph.json","events_json":"https://pith.science/api/pith-number/5SIRHCO5ZT3LDINV7HMWF7K53H/events.json","paper":"https://pith.science/paper/5SIRHCO5"},"agent_actions":{"view_html":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H","download_json":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H.json","view_paper":"https://pith.science/paper/5SIRHCO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10629&json=true","fetch_graph":"https://pith.science/api/pith-number/5SIRHCO5ZT3LDINV7HMWF7K53H/graph.json","fetch_events":"https://pith.science/api/pith-number/5SIRHCO5ZT3LDINV7HMWF7K53H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H/action/storage_attestation","attest_author":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H/action/author_attestation","sign_citation":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H/action/citation_signature","submit_replication":"https://pith.science/pith/5SIRHCO5ZT3LDINV7HMWF7K53H/action/replication_record"}},"created_at":"2026-07-05T09:36:19.498904+00:00","updated_at":"2026-07-05T09:36:19.498904+00:00"}