{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J3R3Z2YMJH7NP6DPJJY3VRH3WO","short_pith_number":"pith:J3R3Z2YM","schema_version":"1.0","canonical_sha256":"4ee3bceb0c49fed7f86f4a71bac4fbb38124180244067d1d7c9e686d74cf92da","source":{"kind":"arxiv","id":"2302.06100","version":2},"attestation_state":"computed","paper":{"title":"Can GPT-3 Perform Statutory Reasoning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Blair-Stanek, Benjamin Van Durme, Nils Holzenberger","submitted_at":"2023-02-13T04:56:11Z","abstract_excerpt":"Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature. It is a basic legal skill. In this paper we explore the capabilities of the most capable GPT-3 model, text-davinci-003, on an established statutory-reasoning dataset called SARA. We consider a variety of approaches, including dynamic few-shot prompting, chain-of-thought prompting, and zero-shot prompting. While we achieve results with GPT-3 that are better than the previous best published results, we also identify several types of clear errors it makes. We investi"},"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":"2302.06100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-13T04:56:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee9ac3675dddae9d55d94c6bd177038fdc8921a95a757851e7c4bc7fbb32a2fd","abstract_canon_sha256":"281b778f1186384ee90be6163f9efd445568f1ae0ba9d99204008d3c422e9bec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:08.355636Z","signature_b64":"plMappdyeOAIPdw1E/bmDpQO/pkDjHaG0VCqayCfea/BPM4DynF9LnNEmL29EkoDOEPunLb2aaFWob0VMTaHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ee3bceb0c49fed7f86f4a71bac4fbb38124180244067d1d7c9e686d74cf92da","last_reissued_at":"2026-07-05T06:09:08.355145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:08.355145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GPT-3 Perform Statutory Reasoning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Blair-Stanek, Benjamin Van Durme, Nils Holzenberger","submitted_at":"2023-02-13T04:56:11Z","abstract_excerpt":"Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature. It is a basic legal skill. In this paper we explore the capabilities of the most capable GPT-3 model, text-davinci-003, on an established statutory-reasoning dataset called SARA. We consider a variety of approaches, including dynamic few-shot prompting, chain-of-thought prompting, and zero-shot prompting. While we achieve results with GPT-3 that are better than the previous best published results, we also identify several types of clear errors it makes. We investi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06100","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/2302.06100/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":"2302.06100","created_at":"2026-07-05T06:09:08.355205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06100v2","created_at":"2026-07-05T06:09:08.355205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06100","created_at":"2026-07-05T06:09:08.355205+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3R3Z2YMJH7N","created_at":"2026-07-05T06:09:08.355205+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3R3Z2YMJH7NP6DP","created_at":"2026-07-05T06:09:08.355205+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3R3Z2YM","created_at":"2026-07-05T06:09:08.355205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25180","citing_title":"DateSAT: A Framework for Solving Date and Period Constraints","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO","json":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO.json","graph_json":"https://pith.science/api/pith-number/J3R3Z2YMJH7NP6DPJJY3VRH3WO/graph.json","events_json":"https://pith.science/api/pith-number/J3R3Z2YMJH7NP6DPJJY3VRH3WO/events.json","paper":"https://pith.science/paper/J3R3Z2YM"},"agent_actions":{"view_html":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO","download_json":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO.json","view_paper":"https://pith.science/paper/J3R3Z2YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06100&json=true","fetch_graph":"https://pith.science/api/pith-number/J3R3Z2YMJH7NP6DPJJY3VRH3WO/graph.json","fetch_events":"https://pith.science/api/pith-number/J3R3Z2YMJH7NP6DPJJY3VRH3WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO/action/storage_attestation","attest_author":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO/action/author_attestation","sign_citation":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO/action/citation_signature","submit_replication":"https://pith.science/pith/J3R3Z2YMJH7NP6DPJJY3VRH3WO/action/replication_record"}},"created_at":"2026-07-05T06:09:08.355205+00:00","updated_at":"2026-07-05T06:09:08.355205+00:00"}