{"record": {"aliases": ["FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models"], "artifacts": [{"id": "arxiv:2608.20153", "kind": "paper", "url": "https://arxiv.org/abs/2608.20153"}], "authors": ["Dingzirui Wang", "Xuanliang Zhang", "Keyan Xu", "Qingfu Zhu", "Wanxiang Che"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.20153", "source_url": "https://arxiv.org/abs/2608.20153"}, "categories": ["Language & Knowledge", "Mathematics & Formal Science", "cs.CL"], "description": {"en": "175 expert-validated instances from STOC, FOCS, SODA, and COLT papers (2025-2026) for evaluating LLMs on end-to-end theoretical computer science research, including autoformalization and proof tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.20153", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.20153", "title": "FormalTCS"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Harbin Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.20153", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.20153", "source_url": "https://openalex.org/W7203938145"}, "key": "claire-radar:2608.20153", "modality": null, "name": "FormalTCS", "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_formaltcs-benchmarking-end-to-end-frontier_6a36f0bb", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "249616690c0b513e3fe3c56b56d31cef2ac8b438c4b3b06ad9768f83fb51cf45", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://arxiv.org/abs/2608.20153"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.20153", "source_url": "https://arxiv.org/abs/2608.20153"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-20153", "source": "claire_radar", "source_benchmark_id": "2608.20153", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models"], "annotation": "Unknown", "applicationDomains": ["Mathematics & Formal Science"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T23:36:26.005677Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.20153", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T23:36:26.005677Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark targets a niche intersection of LLMs and theoretical CS, likely to attract moderate interest from researchers in formal reasoning and theorem proving.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "b35c0d25f67b7596422b02cb7e655b3c65ccde3f437bd809e2ccb54a80d0502c", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models", "canonicalNameSource": "paper_title", "decisionReason": "The paper explicitly defines the benchmark with expert-validated data and clear metrics, and the abstract indicates public availability of the dataset.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "175 expert-validated instances from STOC, FOCS, SODA, and COLT papers (2025-2026) for evaluating LLMs on end-to-end theoretical computer science research, including autoformalization and proof tasks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce \\ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research."}, "familyId": "bmf_26d0fc610574", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_formaltcs-benchmarking-end-to-end-frontier_6a36f0bb", "indexedAt": "2026-08-23T06:55:50.392548Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.20153", "pdf": "https://arxiv.org/pdf/2608.20153", "project": null, "report": "https://arxiv.org/abs/2608.20153"}, "metrics": [], "motivation": "Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings.", "name": "FormalTCS", "oneLine": "175 expert-validated instances from STOC, FOCS, SODA, and COLT papers (2025-2026) for evaluating LLMs on end-to-end theoretical computer science research, including autoformalization and proof tasks.", "paperTitle": "FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.20153", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:50.392548Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-08-20", "source": {"authors": ["Dingzirui Wang", "Xuanliang Zhang", "Keyan Xu", "Qingfu Zhu", "Wanxiang Che"], "categories": ["cs.CL"], "id": "2608.20153", "title": "FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.20153"}, "sourceUpdatedAt": "2026-08-20T15:13:41Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Offers a realistic research evaluation for LLMs in theoretical computer science, highlighting bottlenecks like autoformalization and research taste."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
