{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CEOAA4QU4S6I5S3LX6BYHIDGK7","short_pith_number":"pith:CEOAA4QU","schema_version":"1.0","canonical_sha256":"111c007214e4bc8ecb6bbf8383a06657f7e12f52dfc882b9f2a476cefadb2212","source":{"kind":"arxiv","id":"2406.01940","version":2},"attestation_state":"computed","paper":{"title":"Process-Driven Autoformalization in Lean 4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Chengwu Liu, Haiming Wang, Hui Jin, Jianhao Shen, Jianqiao Lu, Jing Tang, Jing Xiong, Jipeng Zhang, Yingjia Wan, Yinya Huang, Zhengying Liu, Zhicheng Yang, Zhijiang Guo","submitted_at":"2024-06-04T03:48:08Z","abstract_excerpt":"Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning. However, existing efforts are limited to formal languages with substantial online corpora and struggle to keep pace with rapidly evolving languages like Lean 4. To bridge this gap, we propose a new benchmark \\textbf{Form}alization for \\textbf{L}ean~\\textbf{4} (\\textbf{\\name}) designed to evaluate the autoformalization capabilities of large language models (LLMs). This benchmark encompasses a comprehensive assessment of questions, answers, f"},"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":"2406.01940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T03:48:08Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"4e4fbca71c4644d8b6408a510254a7573242f14c482b6d9d191d39b348ff661e","abstract_canon_sha256":"a76c22e7f50958841183cde4b55966ec3dcf493363043e0c8dcb162c8905f8f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:58.102133Z","signature_b64":"vhW6dzzxlaGCM8P3e8RldcVMwlWtJGWvpV/cRm5hFrfgJP7iNWvakkGciGLzb6tq/hQP3sEWGHqxb3buY8W7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111c007214e4bc8ecb6bbf8383a06657f7e12f52dfc882b9f2a476cefadb2212","last_reissued_at":"2026-07-05T09:19:58.101642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:58.101642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Process-Driven Autoformalization in Lean 4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Chengwu Liu, Haiming Wang, Hui Jin, Jianhao Shen, Jianqiao Lu, Jing Tang, Jing Xiong, Jipeng Zhang, Yingjia Wan, Yinya Huang, Zhengying Liu, Zhicheng Yang, Zhijiang Guo","submitted_at":"2024-06-04T03:48:08Z","abstract_excerpt":"Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning. However, existing efforts are limited to formal languages with substantial online corpora and struggle to keep pace with rapidly evolving languages like Lean 4. To bridge this gap, we propose a new benchmark \\textbf{Form}alization for \\textbf{L}ean~\\textbf{4} (\\textbf{\\name}) designed to evaluate the autoformalization capabilities of large language models (LLMs). This benchmark encompasses a comprehensive assessment of questions, answers, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01940","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/2406.01940/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":"2406.01940","created_at":"2026-07-05T09:19:58.101700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01940v2","created_at":"2026-07-05T09:19:58.101700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01940","created_at":"2026-07-05T09:19:58.101700+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEOAA4QU4S6I","created_at":"2026-07-05T09:19:58.101700+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEOAA4QU4S6I5S3L","created_at":"2026-07-05T09:19:58.101700+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEOAA4QU","created_at":"2026-07-05T09:19:58.101700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":156,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31134","citing_title":"Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05729","citing_title":"Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28013","citing_title":"The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31002","citing_title":"Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31134","citing_title":"Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02588","citing_title":"Lean-GAP: A Dataset of Formalized Graduate Algebra Problems","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01008","citing_title":"FVSpec: Real-World Property-Based Tests as Lean Challenges","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23135","citing_title":"Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17255","citing_title":"CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02709","citing_title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23135","citing_title":"Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7","json":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7.json","graph_json":"https://pith.science/api/pith-number/CEOAA4QU4S6I5S3LX6BYHIDGK7/graph.json","events_json":"https://pith.science/api/pith-number/CEOAA4QU4S6I5S3LX6BYHIDGK7/events.json","paper":"https://pith.science/paper/CEOAA4QU"},"agent_actions":{"view_html":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7","download_json":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7.json","view_paper":"https://pith.science/paper/CEOAA4QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01940&json=true","fetch_graph":"https://pith.science/api/pith-number/CEOAA4QU4S6I5S3LX6BYHIDGK7/graph.json","fetch_events":"https://pith.science/api/pith-number/CEOAA4QU4S6I5S3LX6BYHIDGK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7/action/storage_attestation","attest_author":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7/action/author_attestation","sign_citation":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7/action/citation_signature","submit_replication":"https://pith.science/pith/CEOAA4QU4S6I5S3LX6BYHIDGK7/action/replication_record"}},"created_at":"2026-07-05T09:19:58.101700+00:00","updated_at":"2026-07-05T09:19:58.101700+00:00"}