{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JEKOB2FISVHZ6GXXM2KWBGCGMJ","short_pith_number":"pith:JEKOB2FI","schema_version":"1.0","canonical_sha256":"4914e0e8a8954f9f1af766956098466279bac570bc072aabbbc52639bbcd85ce","source":{"kind":"arxiv","id":"2305.05003","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Relation Extraction in the era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byron C. Wallace, Silvio Amir, Somin Wadhwa","submitted_at":"2023-05-08T19:19:07Z","abstract_excerpt":"Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text. Standard supervised RE techniques entail training modules to tag tokens comprising entity spans and then predict the relationship between them. Recent work has instead treated the problem as a \\emph{sequence-to-sequence} task, linearizing relations between entities as target strings to be generated conditioned on the input. Here we push the limits of this approach, using larger language models (GPT-3 and Flan-T5 large) than considered in prior work and evaluating their performance on s"},"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":"2305.05003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-08T19:19:07Z","cross_cats_sorted":[],"title_canon_sha256":"4cad25f7d372f35b00834071bab0b1e3f987ee19235e6de618938e57cfade74c","abstract_canon_sha256":"ac98005fda4a8944ca48cc02aab6840a4625d559b3a089905516499ac91424d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:08.748282Z","signature_b64":"q36XsushfNL2PxJXg4J0R1uOeUjWW8Y8VHTa0C4UwDfdd5NsioDj2sc3J3H6e/BAAUsfsrjPEtyG+UOC/gUDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4914e0e8a8954f9f1af766956098466279bac570bc072aabbbc52639bbcd85ce","last_reissued_at":"2026-07-05T08:44:08.747853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:08.747853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Relation Extraction in the era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byron C. Wallace, Silvio Amir, Somin Wadhwa","submitted_at":"2023-05-08T19:19:07Z","abstract_excerpt":"Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text. Standard supervised RE techniques entail training modules to tag tokens comprising entity spans and then predict the relationship between them. Recent work has instead treated the problem as a \\emph{sequence-to-sequence} task, linearizing relations between entities as target strings to be generated conditioned on the input. Here we push the limits of this approach, using larger language models (GPT-3 and Flan-T5 large) than considered in prior work and evaluating their performance on s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05003","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/2305.05003/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":"2305.05003","created_at":"2026-07-05T08:44:08.747910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05003v2","created_at":"2026-07-05T08:44:08.747910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05003","created_at":"2026-07-05T08:44:08.747910+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEKOB2FISVHZ","created_at":"2026-07-05T08:44:08.747910+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEKOB2FISVHZ6GXX","created_at":"2026-07-05T08:44:08.747910+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEKOB2FI","created_at":"2026-07-05T08:44:08.747910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21222","citing_title":"Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ","json":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ.json","graph_json":"https://pith.science/api/pith-number/JEKOB2FISVHZ6GXXM2KWBGCGMJ/graph.json","events_json":"https://pith.science/api/pith-number/JEKOB2FISVHZ6GXXM2KWBGCGMJ/events.json","paper":"https://pith.science/paper/JEKOB2FI"},"agent_actions":{"view_html":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ","download_json":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ.json","view_paper":"https://pith.science/paper/JEKOB2FI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05003&json=true","fetch_graph":"https://pith.science/api/pith-number/JEKOB2FISVHZ6GXXM2KWBGCGMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JEKOB2FISVHZ6GXXM2KWBGCGMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ/action/storage_attestation","attest_author":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ/action/author_attestation","sign_citation":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ/action/citation_signature","submit_replication":"https://pith.science/pith/JEKOB2FISVHZ6GXXM2KWBGCGMJ/action/replication_record"}},"created_at":"2026-07-05T08:44:08.747910+00:00","updated_at":"2026-07-05T08:44:08.747910+00:00"}