{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WZBUOFLKBPYAXWHUB7DFAXCRA3","short_pith_number":"pith:WZBUOFLK","schema_version":"1.0","canonical_sha256":"b64347156a0bf00bd8f40fc6505c5106e4c6a31e6a62c310f1941fcb6277423b","source":{"kind":"arxiv","id":"2304.11633","version":1},"attestation_state":"computed","paper":{"title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Li, Gexiang Fang, Quansen Wang, Shikun Zhang, Wei Ye, Wen Zhao, Yang Yang","submitted_at":"2023-04-23T12:33:18Z","abstract_excerpt":"The capability of Large Language Models (LLMs) like ChatGPT to comprehend user intent and provide reasonable responses has made them extremely popular lately. In this paper, we focus on assessing the overall ability of ChatGPT using 7 fine-grained information extraction (IE) tasks. Specially, we present the systematically analysis by measuring ChatGPT's performance, explainability, calibration, and faithfulness, and resulting in 15 keys from either the ChatGPT or domain experts. Our findings reveal that ChatGPT's performance in Standard-IE setting is poor, but it surprisingly exhibits excellen"},"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":"2304.11633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-23T12:33:18Z","cross_cats_sorted":[],"title_canon_sha256":"0e0936fa2e52b1274a153aa4c304d3f1173136711b561aedacb78e23b0ae78ad","abstract_canon_sha256":"59975f2183bc3b691429cf5dbdd6e4127b55c4a842bc8c6993f312001424aeba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:35.223111Z","signature_b64":"0qcXXsmjdzBGgErkdHkjp8zwZl0tio+BXQiFKHHx1DIMr1Ees7G6gKrsGZ6OZja7YYkEZK/6m572LoXfcNsWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64347156a0bf00bd8f40fc6505c5106e4c6a31e6a62c310f1941fcb6277423b","last_reissued_at":"2026-07-05T06:03:35.222774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:35.222774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Li, Gexiang Fang, Quansen Wang, Shikun Zhang, Wei Ye, Wen Zhao, Yang Yang","submitted_at":"2023-04-23T12:33:18Z","abstract_excerpt":"The capability of Large Language Models (LLMs) like ChatGPT to comprehend user intent and provide reasonable responses has made them extremely popular lately. In this paper, we focus on assessing the overall ability of ChatGPT using 7 fine-grained information extraction (IE) tasks. Specially, we present the systematically analysis by measuring ChatGPT's performance, explainability, calibration, and faithfulness, and resulting in 15 keys from either the ChatGPT or domain experts. Our findings reveal that ChatGPT's performance in Standard-IE setting is poor, but it surprisingly exhibits excellen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11633","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/2304.11633/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":"2304.11633","created_at":"2026-07-05T06:03:35.222828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11633v1","created_at":"2026-07-05T06:03:35.222828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11633","created_at":"2026-07-05T06:03:35.222828+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZBUOFLKBPYA","created_at":"2026-07-05T06:03:35.222828+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZBUOFLKBPYAXWHU","created_at":"2026-07-05T06:03:35.222828+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZBUOFLK","created_at":"2026-07-05T06:03:35.222828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22606","citing_title":"Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08051","citing_title":"How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29407","citing_title":"LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07738","citing_title":"Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21582","citing_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2305.07895","citing_title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11104","citing_title":"Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3","json":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3.json","graph_json":"https://pith.science/api/pith-number/WZBUOFLKBPYAXWHUB7DFAXCRA3/graph.json","events_json":"https://pith.science/api/pith-number/WZBUOFLKBPYAXWHUB7DFAXCRA3/events.json","paper":"https://pith.science/paper/WZBUOFLK"},"agent_actions":{"view_html":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3","download_json":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3.json","view_paper":"https://pith.science/paper/WZBUOFLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11633&json=true","fetch_graph":"https://pith.science/api/pith-number/WZBUOFLKBPYAXWHUB7DFAXCRA3/graph.json","fetch_events":"https://pith.science/api/pith-number/WZBUOFLKBPYAXWHUB7DFAXCRA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3/action/storage_attestation","attest_author":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3/action/author_attestation","sign_citation":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3/action/citation_signature","submit_replication":"https://pith.science/pith/WZBUOFLKBPYAXWHUB7DFAXCRA3/action/replication_record"}},"created_at":"2026-07-05T06:03:35.222828+00:00","updated_at":"2026-07-05T06:03:35.222828+00:00"}