{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.13782", "kind": "paper", "url": "https://arxiv.org/abs/2606.13782"}, {"id": "gh:openbmb/ma-proofbench", "kind": "repo", "url": "https://github.com/OpenBMB/MA-ProofBench"}], "authors": ["Lushi Pu", "Weiming Zhang", "Xinheng Xie", "Zixuan Fu", "Bingxiang He", "Hongya Lyu", "Xin Li", "Jie Zhou", "Yudong Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.13782", "source_url": "https://arxiv.org/abs/2606.13782"}, "categories": ["Factuality", "Language & Knowledge", "Mathematics & Formal Science", "cs.AI"], "description": {"en": "MA-ProofBench evaluates LLMs on theorem proving in mathematical analysis using 200 Lean 4 formalized problems split into undergraduate and Ph.D. levels. It covers six core topics and uses Pass@8 with formal verification via Lean server."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.13782", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.13782", "title": "MA-ProofBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.13782", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.13782", "source_url": "https://openalex.org/W7164833358"}, "key": "claire-radar:2606.13782", "modality": null, "name": "MA-ProofBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_ma-proofbench_ec795126", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "09b4184520fdee5452c8decd13a4c73afda171a8b344ef138dea6376e343a031", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.13782"}, "publisher": null, "released": "2026-06-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.13782", "source_url": "https://arxiv.org/abs/2606.13782"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-13782", "source": "claire_radar", "source_benchmark_id": "2606.13782", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mathematics & Formal Science"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/OpenBMB/MA-ProofBench", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2606.13782", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "89011505fc7da03fb120410278f5d7b8b383714e7b448165af92d4a4f07f5858", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MA-ProofBench evaluates LLMs on theorem proving in mathematical analysis using 200 Lean 4 formalized problems split into undergraduate and Ph.D. levels. It covers six core topics and uses Pass@8 with formal verification via Lean server.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis."}, "familyId": "bmf_2dea3b94ab49", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/OpenBMB/MA-ProofBench", "url": "https://github.com/OpenBMB/MA-ProofBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/OpenBMB/MA-ProofBench", "url": "https://huggingface.co/papers/2606.13782"}], "scope": "benchmark_repo", "url": "https://github.com/OpenBMB/MA-ProofBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ma-proofbench_ec795126", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/OpenBMB/MA-ProofBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.13782", "paper": "https://arxiv.org/abs/2606.13782", "pdf": "https://arxiv.org/pdf/2606.13782", "project": null, "report": "https://arxiv.org/abs/2606.13782"}, "metrics": [], "motivation": "Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty.", "name": "MA-ProofBench", "oneLine": "MA-ProofBench evaluates LLMs on theorem proving in mathematical analysis using 200 Lean 4 formalized problems split into undergraduate and Ph.D. levels. It covers six core topics and uses Pass@8 with formal verification via Lean server.", "paperTitle": "MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.13782", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "OpenBMB", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/OpenBMB/MA-ProofBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-11", "source": {"authors": ["Lushi Pu", "Weiming Zhang", "Xinheng Xie", "Zixuan Fu", "Bingxiang He", "Hongya Lyu", "Xin Li", "Jie Zhou", "and Yudong Wang"], "categories": ["cs.AI"], "id": "2606.13782", "title": "MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis", "type": "arxiv", "url": "https://arxiv.org/abs/2606.13782"}, "sourceUpdatedAt": "2026-06-15T05:26:47Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Formal theorem proving benchmarks typically lack coverage of advanced analysis. MA-ProofBench fills this gap, providing a stable evaluation for tracking progress in this difficult domain."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
