{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LAMQRSQMP6D7WJSHDMY7D6RD5O","short_pith_number":"pith:LAMQRSQM","schema_version":"1.0","canonical_sha256":"581908ca0c7f87fb26471b31f1fa23eb8f8f8f1f751e14f32836153128aaaeec","source":{"kind":"arxiv","id":"2411.04872","version":7},"attestation_state":"computed","paper":{"title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FrontierMath shows that current AI models solve under 2% of hundreds of original expert-level mathematics problems.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Gunning, Anson Ho, Bogdan Grechuk, Caroline Falkman Olsson, Diego Chicharro, Ege Erdil, Elizabeth Pratt, Elliot Glazer, Emily de Oliveira Santos, Evan Chen, Grant Barkley, Jaime Sevilla, Jean-Stanislas Denain, Lionel Levine, Mark Wildon, Matej Vrzala, Matthew Barnett, Natalie Stewart, Olli J\\\"arviniemi, Qiuyu Ren, Robert Sandler, Shreepranav Varma Enugandla, Tamay Besiroglu, Tetiana Grechuk","submitted_at":"2024-11-07T17:07:35Z","abstract_excerpt":"We introduce FrontierMath, a benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians. The questions cover most major branches of modern mathematics -- from computationally intensive problems in number theory and real analysis to abstract questions in algebraic geometry and category theory. Solving a typical problem requires multiple hours of effort from a researcher in the relevant branch of mathematics, and for the upper end questions, multiple days. FrontierMath uses new, unpublished problems and automated verification to "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.04872","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:07:35Z","cross_cats_sorted":[],"title_canon_sha256":"e39b5e54a321b6dd2a2dcd2586cbb61b3fd68e79c2758b8eeaa45692171d911f","abstract_canon_sha256":"15b96d2206b7385c6251113cf6382dd4dfd673d0492d321994064f46348f4c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.078731Z","signature_b64":"OcYZqz0Zp63FbZvmrI5ZapnieqCfz6D3dG/R6AyMxLeK+Y5JzoS2+yKTnx8/fLdolDnn1I3a7ZfUBilJuH2RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581908ca0c7f87fb26471b31f1fa23eb8f8f8f1f751e14f32836153128aaaeec","last_reissued_at":"2026-05-17T23:38:46.078189Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.078189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FrontierMath shows that current AI models solve under 2% of hundreds of original expert-level mathematics problems.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Gunning, Anson Ho, Bogdan Grechuk, Caroline Falkman Olsson, Diego Chicharro, Ege Erdil, Elizabeth Pratt, Elliot Glazer, Emily de Oliveira Santos, Evan Chen, Grant Barkley, Jaime Sevilla, Jean-Stanislas Denain, Lionel Levine, Mark Wildon, Matej Vrzala, Matthew Barnett, Natalie Stewart, Olli J\\\"arviniemi, Qiuyu Ren, Robert Sandler, Shreepranav Varma Enugandla, Tamay Besiroglu, Tetiana Grechuk","submitted_at":"2024-11-07T17:07:35Z","abstract_excerpt":"We introduce FrontierMath, a benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians. The questions cover most major branches of modern mathematics -- from computationally intensive problems in number theory and real analysis to abstract questions in algebraic geometry and category theory. Solving a typical problem requires multiple hours of effort from a researcher in the relevant branch of mathematics, and for the upper end questions, multiple days. FrontierMath uses new, unpublished problems and automated verification to "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Current state-of-the-art AI models solve under 2% of problems, revealing a vast gap between AI capabilities and the prowess of the mathematical community.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The problems are genuinely original and unpublished with no data contamination risk, and automated verification reliably measures true mathematical reasoning ability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FrontierMath is a new benchmark of hundreds of original hard math problems that current AI models solve less than 2% of.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FrontierMath shows that current AI models solve under 2% of hundreds of original expert-level mathematics problems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1533291bb17f4fcdd10470af2ef410e3853ceefb5e3d0db3efc952c906a1845"},"source":{"id":"2411.04872","kind":"arxiv","version":7},"verdict":{"id":"04ce5a15-2b12-4a1a-bc37-462ab30495b4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:37:28.338908Z","strongest_claim":"Current state-of-the-art AI models solve under 2% of problems, revealing a vast gap between AI capabilities and the prowess of the mathematical community.","one_line_summary":"FrontierMath is a new benchmark of hundreds of original hard math problems that current AI models solve less than 2% of.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The problems are genuinely original and unpublished with no data contamination risk, and automated verification reliably measures true mathematical reasoning ability.","pith_extraction_headline":"FrontierMath shows that current AI models solve under 2% of hundreds of original expert-level mathematics problems."},"references":{"count":32,"sample":[{"doi":"","year":null,"title":"MSC2020 Mathematics Subject Classification System , author =","work_id":"5e2dc496-fa18-47d5-a4ac-19f19351c418","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Training verifiers to solve math word problems, 2021 , author =","work_id":"877a76df-63bd-4ed4-af21-d24219973188","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"d428ff68-61a7-4024-83b4-d1b47a2ad468","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Measuring mathematical problem solving with the math dataset , author =","work_id":"743e28cf-6d1f-4301-a1ce-15d28821dd87","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Math Olympiad Hardness Scale (MOHS) , author =","work_id":"b6a79b50-e6c0-412d-b3e0-21e76a92e058","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"e78a26e92f3862c6e21b005e21fbe7111a5555f6855b742f0ac72d69ddaaadc9","internal_anchors":2},"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":"2411.04872","created_at":"2026-05-17T23:38:46.078262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04872v7","created_at":"2026-05-17T23:38:46.078262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04872","created_at":"2026-05-17T23:38:46.078262+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAMQRSQMP6D7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAMQRSQMP6D7WJSH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAMQRSQM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.09063","citing_title":"Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19338","citing_title":"STAR-P\\'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26574","citing_title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2510.20728","citing_title":"Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":163,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02368","citing_title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13171","citing_title":"Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03789","citing_title":"Automated Conjecture Resolution with Formal Verification","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":213,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09063","citing_title":"Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08905","citing_title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21916","citing_title":"MathDuels: Evaluating LLMs as Problem Posers and Solvers","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18936","citing_title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11535","citing_title":"Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07240","citing_title":"$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06802","citing_title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06107","citing_title":"Artificial Intelligence and the Structure of Mathematics","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04386","citing_title":"Automatically Generating Hard Math Problems from Hypothesis-Driven Error Analysis","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04443","citing_title":"DeonticBench: A Benchmark for Reasoning over Rules","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2501.14249","citing_title":"Humanity's Last Exam","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16646","citing_title":"Agentic Frameworks for Reasoning Tasks: An Empirical Study","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O","json":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O.json","graph_json":"https://pith.science/api/pith-number/LAMQRSQMP6D7WJSHDMY7D6RD5O/graph.json","events_json":"https://pith.science/api/pith-number/LAMQRSQMP6D7WJSHDMY7D6RD5O/events.json","paper":"https://pith.science/paper/LAMQRSQM"},"agent_actions":{"view_html":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O","download_json":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O.json","view_paper":"https://pith.science/paper/LAMQRSQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04872&json=true","fetch_graph":"https://pith.science/api/pith-number/LAMQRSQMP6D7WJSHDMY7D6RD5O/graph.json","fetch_events":"https://pith.science/api/pith-number/LAMQRSQMP6D7WJSHDMY7D6RD5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O/action/storage_attestation","attest_author":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O/action/author_attestation","sign_citation":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O/action/citation_signature","submit_replication":"https://pith.science/pith/LAMQRSQMP6D7WJSHDMY7D6RD5O/action/replication_record"}},"created_at":"2026-05-17T23:38:46.078262+00:00","updated_at":"2026-05-17T23:38:46.078262+00:00"}