{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:62INGKW6DUFMAUW5PJGSP3KQSH","short_pith_number":"pith:62INGKW6","schema_version":"1.0","canonical_sha256":"f690d32ade1d0ac052dd7a4d27ed5091d9cd6f399bcb3e08d2884c81b84d7803","source":{"kind":"arxiv","id":"2409.00369","version":3},"attestation_state":"computed","paper":{"title":"An Empirical Study on Information Extraction using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Chaohao Yang, Lu Liu, Prayag Tiwari, Ridong Han, Tao Peng, Xiang Wan","submitted_at":"2024-08-31T07:10:16Z","abstract_excerpt":"Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI's GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from "},"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":"2409.00369","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-31T07:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"b6f70a1983954aa12e90b4cef93ed1060f2dce14ce570d7b2a97259cd67d8ab7","abstract_canon_sha256":"2bf114a0afc9dce44e260b6e92fc32bce3cf103ab86b1d85468958fc0ac5ce74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:18.701822Z","signature_b64":"qhbUHdkvQsiNO3XkSOSc8Hbycj04pTfTmWDmxf+F92KOkKfOXnEpg0B7KDmQoV+pLSN6SpjZoUXrgKxbMzsNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f690d32ade1d0ac052dd7a4d27ed5091d9cd6f399bcb3e08d2884c81b84d7803","last_reissued_at":"2026-07-05T09:05:18.701358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:18.701358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study on Information Extraction using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Chaohao Yang, Lu Liu, Prayag Tiwari, Ridong Han, Tao Peng, Xiang Wan","submitted_at":"2024-08-31T07:10:16Z","abstract_excerpt":"Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI's GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00369","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/2409.00369/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":"2409.00369","created_at":"2026-07-05T09:05:18.701422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00369v3","created_at":"2026-07-05T09:05:18.701422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00369","created_at":"2026-07-05T09:05:18.701422+00:00"},{"alias_kind":"pith_short_12","alias_value":"62INGKW6DUFM","created_at":"2026-07-05T09:05:18.701422+00:00"},{"alias_kind":"pith_short_16","alias_value":"62INGKW6DUFMAUW5","created_at":"2026-07-05T09:05:18.701422+00:00"},{"alias_kind":"pith_short_8","alias_value":"62INGKW6","created_at":"2026-07-05T09:05:18.701422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04691","citing_title":"SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH","json":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH.json","graph_json":"https://pith.science/api/pith-number/62INGKW6DUFMAUW5PJGSP3KQSH/graph.json","events_json":"https://pith.science/api/pith-number/62INGKW6DUFMAUW5PJGSP3KQSH/events.json","paper":"https://pith.science/paper/62INGKW6"},"agent_actions":{"view_html":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH","download_json":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH.json","view_paper":"https://pith.science/paper/62INGKW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00369&json=true","fetch_graph":"https://pith.science/api/pith-number/62INGKW6DUFMAUW5PJGSP3KQSH/graph.json","fetch_events":"https://pith.science/api/pith-number/62INGKW6DUFMAUW5PJGSP3KQSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH/action/storage_attestation","attest_author":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH/action/author_attestation","sign_citation":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH/action/citation_signature","submit_replication":"https://pith.science/pith/62INGKW6DUFMAUW5PJGSP3KQSH/action/replication_record"}},"created_at":"2026-07-05T09:05:18.701422+00:00","updated_at":"2026-07-05T09:05:18.701422+00:00"}