{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OICZUZXZH6CJ6OLUTN7J4AWQT5","short_pith_number":"pith:OICZUZXZ","schema_version":"1.0","canonical_sha256":"72059a66f93f849f39749b7e9e02d09f75e753f222376f387fe497872cdb3aff","source":{"kind":"arxiv","id":"2305.12196","version":1},"attestation_state":"computed","paper":{"title":"Experimental results from applying GPT-4 to an unpublished formal language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LO","math.LO"],"primary_cat":"cs.CL","authors_text":"Gregor vom Scheidt","submitted_at":"2023-05-20T14:00:08Z","abstract_excerpt":"Can large language models be used to complete mathematical tasks that are traditionally performed either manually or with the aid of theorem provers? To answer this question, a state-of-the-art system, GPT-4, was provided with a concise natural language specification for a previously unpublished formal system and asked to complete a number of tasks, from stating function and type definitions to proving simple theorems and verifying user-supplied proofs. The system completed all tasks successfully, showed extensive domain knowledge, invented helpful new syntax and semantics, and exhibited gener"},"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":"2305.12196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T14:00:08Z","cross_cats_sorted":["cs.LO","math.LO"],"title_canon_sha256":"c5375b543ea7b22d3be3ba2e9c43483fd637aff4d760c38da80000d10bd8df89","abstract_canon_sha256":"f76dd9fb899faf8834f66ddc3f5d2e5784e64d8f0d761ca1007757f6905d03c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:07.519493Z","signature_b64":"ks6ogytH0Feu2uWW7T2kK0AX+BO0cUPwPoRSWjEI9gFdwkz/eNaTpIVm+OJpWtxm9wNUCWVXIsLOj0pDCcM7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72059a66f93f849f39749b7e9e02d09f75e753f222376f387fe497872cdb3aff","last_reissued_at":"2026-07-05T06:12:07.519096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:07.519096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experimental results from applying GPT-4 to an unpublished formal language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LO","math.LO"],"primary_cat":"cs.CL","authors_text":"Gregor vom Scheidt","submitted_at":"2023-05-20T14:00:08Z","abstract_excerpt":"Can large language models be used to complete mathematical tasks that are traditionally performed either manually or with the aid of theorem provers? To answer this question, a state-of-the-art system, GPT-4, was provided with a concise natural language specification for a previously unpublished formal system and asked to complete a number of tasks, from stating function and type definitions to proving simple theorems and verifying user-supplied proofs. The system completed all tasks successfully, showed extensive domain knowledge, invented helpful new syntax and semantics, and exhibited gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12196","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/2305.12196/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":"2305.12196","created_at":"2026-07-05T06:12:07.519156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12196v1","created_at":"2026-07-05T06:12:07.519156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12196","created_at":"2026-07-05T06:12:07.519156+00:00"},{"alias_kind":"pith_short_12","alias_value":"OICZUZXZH6CJ","created_at":"2026-07-05T06:12:07.519156+00:00"},{"alias_kind":"pith_short_16","alias_value":"OICZUZXZH6CJ6OLU","created_at":"2026-07-05T06:12:07.519156+00:00"},{"alias_kind":"pith_short_8","alias_value":"OICZUZXZ","created_at":"2026-07-05T06:12:07.519156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20047","citing_title":"Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5","json":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5.json","graph_json":"https://pith.science/api/pith-number/OICZUZXZH6CJ6OLUTN7J4AWQT5/graph.json","events_json":"https://pith.science/api/pith-number/OICZUZXZH6CJ6OLUTN7J4AWQT5/events.json","paper":"https://pith.science/paper/OICZUZXZ"},"agent_actions":{"view_html":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5","download_json":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5.json","view_paper":"https://pith.science/paper/OICZUZXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12196&json=true","fetch_graph":"https://pith.science/api/pith-number/OICZUZXZH6CJ6OLUTN7J4AWQT5/graph.json","fetch_events":"https://pith.science/api/pith-number/OICZUZXZH6CJ6OLUTN7J4AWQT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5/action/storage_attestation","attest_author":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5/action/author_attestation","sign_citation":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5/action/citation_signature","submit_replication":"https://pith.science/pith/OICZUZXZH6CJ6OLUTN7J4AWQT5/action/replication_record"}},"created_at":"2026-07-05T06:12:07.519156+00:00","updated_at":"2026-07-05T06:12:07.519156+00:00"}