{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.11849", "kind": "paper", "url": "https://arxiv.org/abs/2607.11849"}, {"id": "gh:internlm/advancedmathbench", "kind": "repo", "url": "https://github.com/InternLM/AdvancedMathBench"}], "categories": ["Language & Knowledge", "Mathematics & Formal Science", "Reasoning"], "description": {"en": "AdvancedMathBench is a benchmark suite for advanced mathematical reasoning, containing ProverBench (296 proof problems) and VerifierBench (888 proof trajectories with expert labels), with an automatic verification pipeline."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.11849", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.11849", "title": "AdvancedMathBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.11849", "modality": null, "name": "AdvancedMathBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "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_advancedmathbench_22d95486", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "76ff2477b9aa8fbc820218d9aa6776444dedf91515e167c273d4911f8c20b6bd", "relation": "aggregates", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.11849"}, "publisher": null, "released": "2026-07-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.11849", "source_url": "https://arxiv.org/abs/2607.11849"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-11849", "source": "claire_radar", "source_benchmark_id": "2607.11849", "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/InternLM/AdvancedMathBench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": "2026-07-14T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 29, "hfPaperUrl": "https://huggingface.co/papers/2607.11849", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "cf8c4038b5cb13c25589b51cafb5222643936f34d4177439d46d3b8dfc07f355", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AdvancedMathBench is a benchmark suite for advanced mathematical reasoning, containing ProverBench (296 proof problems) and VerifierBench (888 proof trajectories with expert labels), with an automatic verification pipeline.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To bridge this gap, we introduce AdvancedMathBench, a benchmark suite designed to evaluate advanced mathematical reasoning capabilities."}, "familyId": "bmf_aa5a0a0d601b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_advancedmathbench_22d95486", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/InternLM/AdvancedMathBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.11849", "paper": "https://arxiv.org/abs/2607.11849", "pdf": "https://arxiv.org/pdf/2607.11849", "project": null, "report": "https://arxiv.org/abs/2607.11849"}, "metrics": [], "motivation": "Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics remain poorly understood.", "name": "AdvancedMathBench", "oneLine": "AdvancedMathBench is a benchmark suite for advanced mathematical reasoning, containing ProverBench (296 proof problems) and VerifierBench (888 proof trajectories with expert labels), with an automatic verification pipeline.", "paperTitle": "AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.11849", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.11849"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.6009732431336289, "value": 29}}, "confidence": "Medium", "coverage": 0.7, "rank": 372, "score": 24}, "method": "attention-ranking-v13", "rank": 372, "score": 24}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "aggregates", "releasedAt": "2026-07-13", "source": {"authors": ["Lingkai Kong", "Zijian Wu", "Yuzhe Gu", "Haiteng Zhao", "Wenyong Huang", "Shuang Sun", "Zhicheng Xiong", "Xiaotian Zhang", "Shuya Zhao", "Yan Wang", "Disheng Xu", "Wenwei Zhang", "and Kai Chen"], "categories": ["cs.CL"], "id": "2607.11849", "title": "AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification", "type": "arxiv", "url": "https://arxiv.org/abs/2607.11849"}, "sourceUpdatedAt": "2026-07-13T17:38:22Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing math benchmarks focus on high-school levels and final answers. AdvancedMathBench evaluates proof generation and verification at advanced levels, providing fine-grained assessments of proof correctness and error detection."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
