{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EHSUJMURQGELXBU7ZQ2VNIXQRY","short_pith_number":"pith:EHSUJMUR","schema_version":"1.0","canonical_sha256":"21e544b2918188bb869fcc3556a2f08e20ee5dc3276636a92ae281a0f2f8505c","source":{"kind":"arxiv","id":"2009.03393","version":1},"attestation_state":"computed","paper":{"title":"Generative Language Modeling for Automated Theorem Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Stanislas Polu","submitted_at":"2020-09-07T19:50:10Z","abstract_excerpt":"We explore the application of transformer-based language models to automated theorem proving. This work is motivated by the possibility that a major limitation of automated theorem provers compared to humans -- the generation of original mathematical terms -- might be addressable via generation from language models. We present an automated prover and proof assistant, GPT-f, for the Metamath formalization language, and analyze its performance. GPT-f found new short proofs that were accepted into the main Metamath library, which is to our knowledge, the first time a deep-learning based system ha"},"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":"2009.03393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-07T19:50:10Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"2478595951522e2642935d5e2fc58d6c42689d6e555808b880e2582aa24862cb","abstract_canon_sha256":"bce467e3b6cacf0b5df72d6d63e03bfcc225d8df7adf13f0dcb4476015730933"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-23T05:13:12.891839Z","signature_b64":"iZwNXSsByA8Zq1/dJ+QOY6UYPz88Ojx7dUkOYYuOPCDBAZi3pn9IK30QwTjrYSiowPRuWQXRatBafBONoZCPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21e544b2918188bb869fcc3556a2f08e20ee5dc3276636a92ae281a0f2f8505c","last_reissued_at":"2026-05-23T05:13:12.888873Z","signature_status":"signed_v1","first_computed_at":"2026-05-23T05:13:12.888873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Language Modeling for Automated Theorem Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Stanislas Polu","submitted_at":"2020-09-07T19:50:10Z","abstract_excerpt":"We explore the application of transformer-based language models to automated theorem proving. This work is motivated by the possibility that a major limitation of automated theorem provers compared to humans -- the generation of original mathematical terms -- might be addressable via generation from language models. We present an automated prover and proof assistant, GPT-f, for the Metamath formalization language, and analyze its performance. GPT-f found new short proofs that were accepted into the main Metamath library, which is to our knowledge, the first time a deep-learning based system ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.03393","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/2009.03393/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":"2009.03393","created_at":"2026-05-23T05:13:12.889006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.03393v1","created_at":"2026-05-23T05:13:12.889006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.03393","created_at":"2026-05-23T05:13:12.889006+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHSUJMURQGEL","created_at":"2026-05-23T05:13:12.889006+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHSUJMURQGELXBU7","created_at":"2026-05-23T05:13:12.889006+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHSUJMUR","created_at":"2026-05-23T05:13:12.889006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2402.03300","citing_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":151,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22257","citing_title":"What are the Right Symmetries for Formal Theorem Proving?","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22763","citing_title":"Advancing Mathematics Research with AI-Driven Formal Proof Search","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20244","citing_title":"Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":146,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17255","citing_title":"CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17452","citing_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2310.10631","citing_title":"Llemma: An Open Language Model For Mathematics","ref_index":171,"is_internal_anchor":true},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":213,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2601.20055","citing_title":"VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2402.17762","citing_title":"Massive Activations in Large Language Models","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2602.18843","citing_title":"ABD: Default Exception Abduction in Finite First Order Worlds","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19715","citing_title":"Neuro-Symbolic Proof Generation for Scaling Systems Software Verification","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01346","citing_title":"Aristotle: IMO-level Automated Theorem Proving","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16421","citing_title":"Measuring Representation Robustness in Large Language Models for Geometry","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11905","citing_title":"Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25155","citing_title":"Rethinking Wireless Communications through Formal Mathematical AI Reasoning","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23712","citing_title":"OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2105.09938","citing_title":"Measuring Coding Challenge Competence With APPS","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY","json":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY.json","graph_json":"https://pith.science/api/pith-number/EHSUJMURQGELXBU7ZQ2VNIXQRY/graph.json","events_json":"https://pith.science/api/pith-number/EHSUJMURQGELXBU7ZQ2VNIXQRY/events.json","paper":"https://pith.science/paper/EHSUJMUR"},"agent_actions":{"view_html":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY","download_json":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY.json","view_paper":"https://pith.science/paper/EHSUJMUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.03393&json=true","fetch_graph":"https://pith.science/api/pith-number/EHSUJMURQGELXBU7ZQ2VNIXQRY/graph.json","fetch_events":"https://pith.science/api/pith-number/EHSUJMURQGELXBU7ZQ2VNIXQRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY/action/storage_attestation","attest_author":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY/action/author_attestation","sign_citation":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY/action/citation_signature","submit_replication":"https://pith.science/pith/EHSUJMURQGELXBU7ZQ2VNIXQRY/action/replication_record"}},"created_at":"2026-05-23T05:13:12.889006+00:00","updated_at":"2026-05-23T05:13:12.889006+00:00"}