{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IHNDGGDUQMA5XLL2A5QFFRN2MP","short_pith_number":"pith:IHNDGGDU","schema_version":"1.0","canonical_sha256":"41da3318748301dbad7a076052c5ba63edcb42412b8d69b4784f6f186a634c6c","source":{"kind":"arxiv","id":"2403.12627","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Formal Theorem Proving: A Comprehensive Dataset for Training AI Models on Coq Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Andreas Florath","submitted_at":"2024-03-19T10:53:40Z","abstract_excerpt":"In the realm of formal theorem proving, the Coq proof assistant stands out for its rigorous approach to verifying mathematical assertions and software correctness. Despite the advances in artificial intelligence and machine learning, the specialized nature of Coq syntax and semantics poses unique challenges for Large Language Models (LLMs). Addressing this gap, we present a comprehensive dataset specifically designed to enhance LLMs' proficiency in interpreting and generating Coq code. This dataset, derived from a collection of over 10,000 Coq source files, encompasses a wide array of proposit"},"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":"2403.12627","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-19T10:53:40Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"1bb2fff1801da15cc71fb0f70cbef0b18ed2612f70102bf511ad59572388bcc3","abstract_canon_sha256":"76c506cb30be863c3e6a16048374655de3c13d32dbb0aee2b63cd033864105c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:29.765773Z","signature_b64":"oTl60FUzF2OaFEFXVLjp2ey9uFxDVROZhMoUCQdQU38MIaIasgmaf5GUT6fdTJoJs+Irx0qQfazQ2idMioaFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41da3318748301dbad7a076052c5ba63edcb42412b8d69b4784f6f186a634c6c","last_reissued_at":"2026-07-05T08:03:29.765359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:29.765359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Formal Theorem Proving: A Comprehensive Dataset for Training AI Models on Coq Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Andreas Florath","submitted_at":"2024-03-19T10:53:40Z","abstract_excerpt":"In the realm of formal theorem proving, the Coq proof assistant stands out for its rigorous approach to verifying mathematical assertions and software correctness. Despite the advances in artificial intelligence and machine learning, the specialized nature of Coq syntax and semantics poses unique challenges for Large Language Models (LLMs). Addressing this gap, we present a comprehensive dataset specifically designed to enhance LLMs' proficiency in interpreting and generating Coq code. This dataset, derived from a collection of over 10,000 Coq source files, encompasses a wide array of proposit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12627","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/2403.12627/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":"2403.12627","created_at":"2026-07-05T08:03:29.765412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12627v2","created_at":"2026-07-05T08:03:29.765412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12627","created_at":"2026-07-05T08:03:29.765412+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHNDGGDUQMA5","created_at":"2026-07-05T08:03:29.765412+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHNDGGDUQMA5XLL2","created_at":"2026-07-05T08:03:29.765412+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHNDGGDU","created_at":"2026-07-05T08:03:29.765412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02541","citing_title":"Clarifying Before Reasoning: A Coq Prover with Structural Context","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP","json":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP.json","graph_json":"https://pith.science/api/pith-number/IHNDGGDUQMA5XLL2A5QFFRN2MP/graph.json","events_json":"https://pith.science/api/pith-number/IHNDGGDUQMA5XLL2A5QFFRN2MP/events.json","paper":"https://pith.science/paper/IHNDGGDU"},"agent_actions":{"view_html":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP","download_json":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP.json","view_paper":"https://pith.science/paper/IHNDGGDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12627&json=true","fetch_graph":"https://pith.science/api/pith-number/IHNDGGDUQMA5XLL2A5QFFRN2MP/graph.json","fetch_events":"https://pith.science/api/pith-number/IHNDGGDUQMA5XLL2A5QFFRN2MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP/action/storage_attestation","attest_author":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP/action/author_attestation","sign_citation":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP/action/citation_signature","submit_replication":"https://pith.science/pith/IHNDGGDUQMA5XLL2A5QFFRN2MP/action/replication_record"}},"created_at":"2026-07-05T08:03:29.765412+00:00","updated_at":"2026-07-05T08:03:29.765412+00:00"}