{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25286", "kind": "paper", "url": "https://arxiv.org/abs/2608.25286"}], "authors": ["Zane Koch", "Asmamaw T. Wassie", "Javier Valdes-Aleman", "Jason Lee", "Michaela M. Hinks", "Samuel G. Rodriques", "Andrew D. White", "Jon M. Laurent"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25286", "source_url": "https://arxiv.org/abs/2608.25286"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates AI agents on 20 research-study-scale computational biology tasks that require processing raw data into scientific results, scored by matching generated artifacts against study-derived targets."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25286", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25286", "title": "BixBench3"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Edison Scientific Inc. (United States)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.25286", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.25286", "source_url": "https://openalex.org/W7204493988"}, "key": "claire-radar:2608.25286", "modality": null, "name": "BixBench3", "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_bixbench3_ede996e4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1115249b103c3083dd9edc006b5e4150c32f79287fc57441e6e33f2851e236cc", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.25286"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25286", "source_url": "https://arxiv.org/abs/2608.25286"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25286", "source": "claire_radar", "source_benchmark_id": "2608.25286", "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/2608.25286", "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 benchmark addresses a high-impact scientific domain and reports performance across many frontier models, but missing artifacts may reduce immediate attention.", "score": 60}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "0a7edf95f14cdbd800d23c121f31be45a70353fd30d4bce82cf9f4496b410fc9", "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 AI agents on 20 research-study-scale computational biology tasks that require processing raw data into scientific results, scored by matching generated artifacts against study-derived targets.", "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": "Here we introduce BixBench3, a benchmark that measures the capacity of AI agents to process raw biological data through to scientific results."}, "familyId": "bmf_113a1bb4bad5", "firstSeenAt": "2026-08-29", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_bixbench3_ede996e4", "indexedAt": "2026-08-29T08:02:23.506802Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.25286", "paper": "https://arxiv.org/abs/2608.25286", "pdf": "https://arxiv.org/pdf/2608.25286", "project": null, "report": "https://arxiv.org/abs/2608.25286"}, "metrics": [], "motivation": "Artificial intelligence (AI) promises to accelerate biological research by automating computational analyses.", "name": "BixBench3", "oneLine": "Evaluates AI agents on 20 research-study-scale computational biology tasks that require processing raw data into scientific results, scored by matching generated artifacts against study-derived targets.", "paperTitle": "BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.25286", "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": "2026-08-26", "source": {"authors": ["Zane Koch", "Asmamaw T. Wassie", "Javier Valdes-Aleman", "Jason Lee", "Michaela M. Hinks", "Samuel G. Rodriques", "Andrew D. White", "Jon M. Laurent"], "categories": ["cs.AI", "q-bio.QM"], "id": "2608.25286", "title": "BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25286"}, "sourceUpdatedAt": "2026-08-26T01:45:55Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Systematically measures agent capability in long-horizon, data-intensive biological analyses, revealing gaps in sequential reasoning and resource management."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
