{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.11941", "kind": "paper", "url": "https://arxiv.org/abs/2608.11941"}, {"id": "gh:epoch-research/leanopenproblems", "kind": "repo", "url": "https://github.com/epoch-research/LeanOpenProblems"}], "authors": ["Tom Adamczewski"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.11941", "source_url": "https://arxiv.org/abs/2608.11941"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates language models on formalized open mathematical conjectures from OEIS, scored by theorem resolution under a compute budget."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.11941", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.11941", "title": "OEIS Open"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.11941", "modality": null, "name": "OEIS Open", "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": "true", "origin_record_id": "bm_oeis-open_86208c3e", "origin_source": "arxiv", "recognition_confidence": "0.8", "record_sha256": "fba168ad77602d562dffb8cb31cbedb4f26153e783ee36b513e4d88977db5a5e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:14:52.836173Z", "source_url": "https://arxiv.org/abs/2608.11941"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.11941", "source_url": "https://arxiv.org/abs/2608.11941"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-11941", "source": "claire_radar", "source_benchmark_id": "2608.11941", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/epoch-research/LeanOpenProblems", "githubScope": "benchmark_repo", "githubStars": 16, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.11941", "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": "The benchmark targets the niche area of formalized math conjectures with modest language model capabilities, though specific adoption signals are absent.", "score": 68}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:14:52.836173Z", "inputHash": "539f099b28cbb32ccb0eb36c086c58837faeea7535a33600f7a3cd9bb149d408", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We construct OEIS Open, a benchmark based on 492 open mathematical conjectures", "canonicalNameSource": "abstract", "decisionReason": "OEIS Open is a named benchmark with open-source evaluation code and results repositories, enabling reuse by other teams.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:14:52.836173Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates language models on formalized open mathematical conjectures from OEIS, scored by theorem resolution under a compute budget.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "public artifact URL"], "snippet": "We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al."}, "familyId": "bmf_5120c16b457f", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_oeis-open_86208c3e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/epoch-research/LeanOpenProblems", "data": null, "paper": "https://arxiv.org/abs/2608.11941", "pdf": "https://arxiv.org/pdf/2608.11941", "project": null, "report": "https://arxiv.org/abs/2608.11941"}, "metrics": [], "motivation": "We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al.", "name": "OEIS Open", "oneLine": "Evaluates language models on formalized open mathematical conjectures from OEIS, scored by theorem resolution under a compute budget.", "paperTitle": "OEIS Open: How many conjectures can language models turn into theorems?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.11941", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "Epoch AI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/epoch-research/LeanOpenProblems"}], "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": 0.37818305124532486, "value": 16}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 119, "score": 43}, "method": "attention-ranking-v13", "rank": 119, "score": 43}}, "readiness": "Runnable", "recognitionConfidence": 0.8, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Tom Adamczewski"], "categories": ["cs.AI"], "id": "2608.11941", "title": "OEIS Open: How many conjectures can language models turn into theorems?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.11941"}, "sourceUpdatedAt": "2026-08-13T09:23:24Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It provides a secure, reproducible suite for testing autonomous mathematical reasoning on open problems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
