{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.09264", "kind": "paper", "url": "https://arxiv.org/abs/2609.09264"}], "authors": ["Idan Davidovich", "Debargha Ganguly", "Vikash Singh", "Vipin Chaudhary"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.09264", "source_url": "https://arxiv.org/abs/2609.09264"}, "categories": ["Language & Knowledge", "Mathematics & Formal Science", "cs.CL"], "description": {"en": "A Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.09264", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.09264", "title": "StochBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Case Western Reserve University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.09264", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.09264", "source_url": "https://openalex.org/W7212133990"}, "key": "claire-radar:2609.09264", "modality": null, "name": "StochBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_stochbench_a640a158", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "15f3184f5a4e1a3af3ade024e984d703ae434d5e0ef460e72364dc24cf011803", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-12T00:56:20.009268Z", "source_url": "https://arxiv.org/abs/2609.09264"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.09264", "source_url": "https://arxiv.org/abs/2609.09264"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-09264", "source": "claire_radar", "source_benchmark_id": "2609.09264", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": "2026-09-10T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 8, "hfPaperUrl": "https://huggingface.co/papers/2609.09264", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The formal-math community is small, and without released artifacts the benchmark is unlikely to draw fast attention.", "score": 30}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-12T00:56:20.009268Z", "inputHash": "acb0bf228125bb551d0a3caf4645e30b21a77c90b1212ff916a174cec1474c25", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source.", "canonicalNameSource": "abstract", "decisionReason": "No artifact evidence or public submission path is supplied, preventing verification of task availability or evaluation protocol.", "evaluationEvidence": {"reuse": "StochBench provides a domain-specific benchmark for formal theorem proving, enabling evaluation of different LLM-based provers on stochastic processes problems.", "scoring": "The benchmark reports proof rate, with an Opus 4.8-based agent achieving 34.9% proof rate under a 15-minute per-problem limit.", "task": "StochBench is a Lean 4 benchmark of 450 graduate stochastic-processes problems covering finite and countable Markov chains, renewal processes, random walks, martingales, stopping times, queues, Brownian motion, stochastic calculus, weak convergence, and Poisson and continuous-time Markov processes."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-12T00:56:20.009268Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source."}, "familyId": "bmf_fa81ce21230f", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_stochbench_a640a158", "indexedAt": "2026-09-10T00:47:26.889471Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.09264", "pdf": "https://arxiv.org/pdf/2609.09264", "project": null, "report": "https://arxiv.org/abs/2609.09264"}, "metrics": [], "motivation": "Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications.", "name": "StochBench", "oneLine": "A Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source.", "paperTitle": "StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.09264", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-10T00:47:26.889471Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.3, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.40911797924728627, "value": 8}}, "confidence": "Low", "coverage": 0.3, "rank": null, "score": 47}, "method": "attention-ranking-v13", "rank": null, "score": 47}, "90d": {"confidence": "Low", "coverage": 0.15, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.3882377386428991, "value": 8}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 48}, "method": "attention-ranking-v13", "rank": null, "score": 48}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-09-08", "source": {"authors": ["Idan Davidovich", "Debargha Ganguly", "Vikash Singh", "Vipin Chaudhary"], "categories": ["cs.CL", "cs.LO"], "id": "2609.09264", "title": "StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean", "type": "arxiv", "url": "https://arxiv.org/abs/2609.09264"}, "sourceUpdatedAt": "2026-09-08T17:59:46Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Formalization benchmarks can measure progress in automated theorem proving for advanced mathematical domains."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
