{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ND642VONYN5WNXZO4ULUNUVABN","short_pith_number":"pith:ND642VON","schema_version":"1.0","canonical_sha256":"68fdcd55cdc37b66df2ee51746d2a00b7fb225f2f241768dade69008960089bf","source":{"kind":"arxiv","id":"2407.11214","version":2},"attestation_state":"computed","paper":{"title":"PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.LO","cs.PL"],"primary_cat":"cs.AI","authors_text":"Amitayush Thakur, George Tsoukalas, Jasper Lee, Jimmy Xin, John Jennings, Michael Jennings, Michelle Ding, Swarat Chaudhuri","submitted_at":"2024-07-15T19:57:15Z","abstract_excerpt":"We present PutnamBench, a new multi-language benchmark for evaluating the ability of neural theorem-provers to solve competition mathematics problems. PutnamBench consists of 1692 hand-constructed formalizations of 640 theorems sourced from the William Lowell Putnam Mathematical Competition, the premier undergraduate-level mathematics competition in North America. All the problems have formalizations in Lean 4 and Isabelle; a substantial subset also has Coq formalizations. PutnamBench requires significant problem-solving ability and proficiency in a broad range of topics taught in undergraduat"},"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":"2407.11214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T19:57:15Z","cross_cats_sorted":["cs.CL","cs.LG","cs.LO","cs.PL"],"title_canon_sha256":"1f39aa8b391f68a6c7f2c6e842c5e48155744c43f449414a6f9aec1152dcd083","abstract_canon_sha256":"d2d84a5d2d81b32134bed4a6b8faef01772e38464b232d5618ce8c1e10194e36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:18.860756Z","signature_b64":"c3ShUE822hryl1VACE4wzgpXfmFIjuAax9v8fRq3IxUdY/bj80a13f/Fg0iGG07QAEOM95FPlSeigp4wiwprAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68fdcd55cdc37b66df2ee51746d2a00b7fb225f2f241768dade69008960089bf","last_reissued_at":"2026-07-05T09:30:18.860273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:18.860273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.LO","cs.PL"],"primary_cat":"cs.AI","authors_text":"Amitayush Thakur, George Tsoukalas, Jasper Lee, Jimmy Xin, John Jennings, Michael Jennings, Michelle Ding, Swarat Chaudhuri","submitted_at":"2024-07-15T19:57:15Z","abstract_excerpt":"We present PutnamBench, a new multi-language benchmark for evaluating the ability of neural theorem-provers to solve competition mathematics problems. PutnamBench consists of 1692 hand-constructed formalizations of 640 theorems sourced from the William Lowell Putnam Mathematical Competition, the premier undergraduate-level mathematics competition in North America. All the problems have formalizations in Lean 4 and Isabelle; a substantial subset also has Coq formalizations. PutnamBench requires significant problem-solving ability and proficiency in a broad range of topics taught in undergraduat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11214","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/2407.11214/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":"2407.11214","created_at":"2026-07-05T09:30:18.860337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11214v2","created_at":"2026-07-05T09:30:18.860337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11214","created_at":"2026-07-05T09:30:18.860337+00:00"},{"alias_kind":"pith_short_12","alias_value":"ND642VONYN5W","created_at":"2026-07-05T09:30:18.860337+00:00"},{"alias_kind":"pith_short_16","alias_value":"ND642VONYN5WNXZO","created_at":"2026-07-05T09:30:18.860337+00:00"},{"alias_kind":"pith_short_8","alias_value":"ND642VON","created_at":"2026-07-05T09:30:18.860337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18050","citing_title":"The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25363","citing_title":"TheoremGraph: Bridging Formal and Informal Mathematics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09450","citing_title":"TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01861","citing_title":"A Theoretical Framework for Self-Play Theorem Proving Algorithms","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27485","citing_title":"Automating Formal Verification with Agent-Guided Tree Search","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2504.11354","citing_title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01346","citing_title":"Aristotle: IMO-level Automated Theorem Proving","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23281","citing_title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13171","citing_title":"Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06802","citing_title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06107","citing_title":"Artificial Intelligence and the Structure of Mathematics","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2501.14249","citing_title":"Humanity's Last Exam","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18050","citing_title":"The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15839","citing_title":"Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN","json":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN.json","graph_json":"https://pith.science/api/pith-number/ND642VONYN5WNXZO4ULUNUVABN/graph.json","events_json":"https://pith.science/api/pith-number/ND642VONYN5WNXZO4ULUNUVABN/events.json","paper":"https://pith.science/paper/ND642VON"},"agent_actions":{"view_html":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN","download_json":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN.json","view_paper":"https://pith.science/paper/ND642VON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11214&json=true","fetch_graph":"https://pith.science/api/pith-number/ND642VONYN5WNXZO4ULUNUVABN/graph.json","fetch_events":"https://pith.science/api/pith-number/ND642VONYN5WNXZO4ULUNUVABN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN/action/storage_attestation","attest_author":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN/action/author_attestation","sign_citation":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN/action/citation_signature","submit_replication":"https://pith.science/pith/ND642VONYN5WNXZO4ULUNUVABN/action/replication_record"}},"created_at":"2026-07-05T09:30:18.860337+00:00","updated_at":"2026-07-05T09:30:18.860337+00:00"}