{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F3KD7ODL3VCWL746DJ22HY5NHV","short_pith_number":"pith:F3KD7ODL","schema_version":"1.0","canonical_sha256":"2ed43fb86bdd4565ff9e1a75a3e3ad3d445e4bc469a6666886df475dd7fa6e79","source":{"kind":"arxiv","id":"2501.16207","version":4},"attestation_state":"computed","paper":{"title":"From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.AI","authors_text":"Cheng Wen, Cong Tian, Haokun Li, Haoyang Ma, Hongyu Zhang, Jialun Cao, Le Sun, Meiziniu Li, Mengda He, Shengchao Qin, Shing-Chi Cheung, Yaojie Lu","submitted_at":"2025-01-27T17:00:56Z","abstract_excerpt":"The research in AI-based formal mathematical reasoning has shown an unstoppable growth trend. These studies have excelled in mathematical competitions like IMO and have made significant progress. This paper focuses on formal verification, an immediate application scenario of formal reasoning, and breaks it down into sub-tasks. We constructed 18k high-quality instruction-response pairs across five formal specification languages (Coq, Lean4, Dafny, ACSL, and TLA+) by distilling gpt-4o and evaluated against ten open-sourced LLMs, including recent popular DeepSeek-R1. We also fine-tuned several 7~"},"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":"2501.16207","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-27T17:00:56Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"12cae7dc74e32e91a5bcbf5c66d724dce964e5607394f9e6d78abc515167cd26","abstract_canon_sha256":"ba6fe801fce7c2b1cb48d7699f69cdb9c94974d79181204ebe4c71b337a56e9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:40.145831Z","signature_b64":"mHM1Hh0IZ7rDwMs+doyzJd0q/yEAgQbAOuI1aaVoZ4z5NB1G/v9kb1xZNXC3O7UPFYl9cbgTrqKwkQhG3MWxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed43fb86bdd4565ff9e1a75a3e3ad3d445e4bc469a6666886df475dd7fa6e79","last_reissued_at":"2026-07-05T11:17:40.145331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:40.145331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.AI","authors_text":"Cheng Wen, Cong Tian, Haokun Li, Haoyang Ma, Hongyu Zhang, Jialun Cao, Le Sun, Meiziniu Li, Mengda He, Shengchao Qin, Shing-Chi Cheung, Yaojie Lu","submitted_at":"2025-01-27T17:00:56Z","abstract_excerpt":"The research in AI-based formal mathematical reasoning has shown an unstoppable growth trend. These studies have excelled in mathematical competitions like IMO and have made significant progress. This paper focuses on formal verification, an immediate application scenario of formal reasoning, and breaks it down into sub-tasks. We constructed 18k high-quality instruction-response pairs across five formal specification languages (Coq, Lean4, Dafny, ACSL, and TLA+) by distilling gpt-4o and evaluated against ten open-sourced LLMs, including recent popular DeepSeek-R1. We also fine-tuned several 7~"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16207","kind":"arxiv","version":4},"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/2501.16207/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":"2501.16207","created_at":"2026-07-05T11:17:40.145397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16207v4","created_at":"2026-07-05T11:17:40.145397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16207","created_at":"2026-07-05T11:17:40.145397+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3KD7ODL3VCW","created_at":"2026-07-05T11:17:40.145397+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3KD7ODL3VCWL746","created_at":"2026-07-05T11:17:40.145397+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3KD7ODL","created_at":"2026-07-05T11:17:40.145397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21570","citing_title":"SpecSyn: LLM-based Synthesis and Refinement of Formal Specifications for Real-world Program Verification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV","json":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV.json","graph_json":"https://pith.science/api/pith-number/F3KD7ODL3VCWL746DJ22HY5NHV/graph.json","events_json":"https://pith.science/api/pith-number/F3KD7ODL3VCWL746DJ22HY5NHV/events.json","paper":"https://pith.science/paper/F3KD7ODL"},"agent_actions":{"view_html":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV","download_json":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV.json","view_paper":"https://pith.science/paper/F3KD7ODL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16207&json=true","fetch_graph":"https://pith.science/api/pith-number/F3KD7ODL3VCWL746DJ22HY5NHV/graph.json","fetch_events":"https://pith.science/api/pith-number/F3KD7ODL3VCWL746DJ22HY5NHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV/action/storage_attestation","attest_author":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV/action/author_attestation","sign_citation":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV/action/citation_signature","submit_replication":"https://pith.science/pith/F3KD7ODL3VCWL746DJ22HY5NHV/action/replication_record"}},"created_at":"2026-07-05T11:17:40.145397+00:00","updated_at":"2026-07-05T11:17:40.145397+00:00"}