{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.23898", "kind": "paper", "url": "https://arxiv.org/abs/2608.23898"}], "authors": ["Aditya Sivakumar", "Ashu Singhal", "Nicholas Larus-Stone", "Nithin Parsan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23898", "source_url": "https://arxiv.org/abs/2608.23898"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Evaluates LLMs on 149 protocol-modification tasks reconstructed from real changes scientists made to published wet-lab protocols, using weighted rubric scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23898", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23898", "title": "BenchBench-Protocol"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.23898", "modality": null, "name": "BenchBench-Protocol", "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_benchbench-protocol_1d14c082", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "307543d33d5ccbe32504c2f56c0fba8a2ad893dd0c6ff02ca585970ed240b911", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.23898"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23898", "source_url": "https://arxiv.org/abs/2608.23898"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23898", "source": "claire_radar", "source_benchmark_id": "2608.23898", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.23898", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The novelty of real-world protocol modification tasks and life-science relevance may attract moderate attention, but lack of public artifacts and a preprint-only source temper the forecast.", "score": 35}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "1fa85de3c2f40f379a057f95ae025b309c06de0a2e2d6f877c66fc53087801b9", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLMs on 149 protocol-modification tasks reconstructed from real changes scientists made to published wet-lab protocols, using weighted rubric scoring.", "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"], "snippet": "We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification tasks recovered from modifications that scientists made to published protocols during real experimental work."}, "familyId": "bmf_bee0f754351c", "firstSeenAt": "2026-08-27", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_benchbench-protocol_1d14c082", "indexedAt": "2026-08-27T11:43:23.081477Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.23898", "paper": "https://arxiv.org/abs/2608.23898", "pdf": "https://arxiv.org/pdf/2608.23898", "project": null, "report": "https://arxiv.org/abs/2608.23898"}, "metrics": [], "motivation": "We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification tasks recovered from modifications that scientists made to published protocols during real experimental work.", "name": "BenchBench-Protocol", "oneLine": "Evaluates LLMs on 149 protocol-modification tasks reconstructed from real changes scientists made to published wet-lab protocols, using weighted rubric scoring.", "paperTitle": "BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.23898", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Aditya Sivakumar", "Ashu Singhal", "Nicholas Larus-Stone", "and Nithin Parsan"], "categories": ["cs.AI"], "id": "2608.23898", "title": "BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification", "type": "arxiv", "url": "https://arxiv.org/abs/2608.23898"}, "sourceUpdatedAt": "2026-08-24T23:11:35Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Assesses routine wet-lab adaptation reasoning from real experimental modifications, filling a gap in grounded life-science evaluation beyond expert-elicited tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
