{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25449", "kind": "paper", "url": "https://arxiv.org/abs/2608.25449"}, {"id": "gh:margotyjx/mathadv", "kind": "repo", "url": "https://github.com/margotyjx/MathAdv.git"}], "authors": ["Jiaxin Yuan", "Udari Madhushani Sehwag", "Connor Martinez Lockhart", "Xiaoyu Liu", "Shayan Shabihi", "Jiaqi Wang", "Chenghao Deng", "Xiayimei Han", "Vlassis Mastrantonis", "Dmitrii Gudin", "Shaopeng Zhu", "Abdirisak Mohamed", "Bilal Aytekin", "Jiewen Lang", "Zezheng Song", "Furong Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25449", "source_url": "https://arxiv.org/abs/2608.25449"}, "categories": ["General AI", "Language & Knowledge", "Mathematics & Formal Science", "cs.CL"], "description": {"en": "Evaluates theorem proving and auxiliary tasks including multiple-choice, fill-in-the-blank, and reformulation robustness across 13 mathematical domains."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25449", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25449", "title": "MathAdv"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Maryland, College Park", "Georgia Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.25449", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.25449", "source_url": "https://openalex.org/W7204466545"}, "key": "claire-radar:2608.25449", "modality": null, "name": "MathAdv", "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": "true", "origin_record_id": "bm_mathadv_85c33564", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b82c4a1d1a8c9950375f202a1c5237df016fde812b4b935f4c3c1dad02b249ec", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:12:36.511123Z", "source_url": "https://arxiv.org/abs/2608.25449"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25449", "source_url": "https://arxiv.org/abs/2608.25449"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25449", "source": "claire_radar", "source_benchmark_id": "2608.25449", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI", "Mathematics & Formal Science"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/margotyjx/MathAdv", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.25449", "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", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Focused formal theorem proving benchmark with diagnostic tasks, but limited to Lean 4 and linked repository status unverified.", "score": 50}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "4f9d6ce04f6ec7b8e469791e82f2bb6f6da1ef56912619d78c5d2c3c55b77b52", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce MathAdv, a diagnostic benchmark spanning 13 domains across undergraduate- and graduate-level mathematics.", "canonicalNameSource": "abstract", "decisionReason": "MathAdv is explicitly named and described as a benchmark, and the abstract reports dataset and evaluation scripts available on GitHub, though the link is unverified.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:12:36.511123Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates theorem proving and auxiliary tasks including multiple-choice, fill-in-the-blank, and reformulation robustness across 13 mathematical domains.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce MathAdv, a diagnostic benchmark spanning 13 domains across undergraduate- and graduate-level mathematics."}, "familyId": "bmf_9e215fa673d4", "firstSeenAt": "2026-08-27", "heat": null, "id": "bm_mathadv_85c33564", "indexedAt": "2026-08-27T04:12:10.575570Z", "industrySectors": [], "links": {"code": "https://github.com/margotyjx/MathAdv.git", "data": null, "paper": "https://arxiv.org/abs/2608.25449", "pdf": "https://arxiv.org/pdf/2608.25449", "project": null, "report": "https://arxiv.org/abs/2608.25449"}, "metrics": [], "motivation": "Formal theorem proving enables machine-verifiable evaluation of mathematical reasoning, yet existing benchmarks often emphasize aggregate proof accuracy, concentrate on a narrow range of mathematics, and provide limited evidence of robustness to equivalent reformulations.", "name": "MathAdv", "oneLine": "Evaluates theorem proving and auxiliary tasks including multiple-choice, fill-in-the-blank, and reformulation robustness across 13 mathematical domains.", "paperTitle": "MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.25449", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-27T04:12:10.575570Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 224, "score": 33}, "method": "attention-ranking-v13", "rank": 224, "score": 33}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-26", "source": {"authors": ["Jiaxin Yuan", "Connor Martinez Lockhart", "Xiaoyu Liu", "Jiaqi Wang", "Chenghao Deng", "Xiayimei Han", "Vlasios Mastrantonis", "Dmitrii Gudin", "Shaopeng Zhu", "Abdirisak Abdullahi Mohamed", "Bilal Hamdi Aytekin", "Jiewen Lang", "Zezheng Song", "Furong Huang"], "categories": ["cs.CL", "cs.AI", "cs.LO"], "id": "2608.25449", "title": "MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25449"}, "sourceUpdatedAt": "2026-08-26T07:12:54Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Offers component-wise diagnosis of formal reasoning beyond aggregate proof accuracy, exposing formalization and robustness gaps."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
