{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.26563", "kind": "paper", "url": "https://arxiv.org/abs/2606.26563"}], "authors": ["Ian Diks", "Zhen Yang", "Arjun Banerjee", "Tim Proctor", "Kenny Workman"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.26563", "source_url": "https://arxiv.org/abs/2606.26563"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "q-bio.GN"], "description": {"en": "scBench-Long evaluates long-horizon single-cell biology reasoning. Agents must recover scientific conclusions from raw or near-raw data without prescribed methods. It contains 21 evaluations spanning diverse biological contexts, with deterministic grading and trajectory rubrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.26563", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.26563", "title": "scBench-Long"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.26563", "modality": null, "name": "scBench-Long", "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": "unknown", "origin_record_id": "bm_scbench-long_49d2490a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "488f393f74d794fb0c7a65f3aaee8691abad691b9dd899c8e588c74e071a30c0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.26563"}, "publisher": null, "released": "2026-06-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.26563", "source_url": "https://arxiv.org/abs/2606.26563"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-26563", "source": "claire_radar", "source_benchmark_id": "2606.26563", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "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/2606.26563", "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"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "0ce8128d983bac74942c4aee784ff35a4f35064bc94ddcb88f4b278bcc660cb9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "scBench-Long evaluates long-horizon single-cell biology reasoning. Agents must recover scientific conclusions from raw or near-raw data without prescribed methods. It contains 21 evaluations spanning diverse biological contexts, with deterministic grading and trajectory rubrics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce scBench-Long, a benchmark for long-horizon single-cell biology in which agents must recover scientific conclusions from raw or near-raw data without prescribed methods."}, "familyId": "bmf_8fb55cb2c14b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_scbench-long_49d2490a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.26563", "paper": "https://arxiv.org/abs/2606.26563", "pdf": "https://arxiv.org/pdf/2606.26563", "project": null, "report": "https://arxiv.org/abs/2606.26563"}, "metrics": [], "motivation": "Single-cell studies require analysts to convert raw measurements into specific biological claims through multi-step workflows and integration of metadata, assay context, and auxiliary evidence.", "name": "scBench-Long", "oneLine": "scBench-Long evaluates long-horizon single-cell biology reasoning. Agents must recover scientific conclusions from raw or near-raw data without prescribed methods. It contains 21 evaluations spanning diverse biological contexts, with deterministic grading and trajectory rubrics.", "paperTitle": "scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.26563", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-25", "source": {"authors": ["Ian Diks", "Zhen Yang", "Arjun Banerjee", "Tim Proctor", "Kenny Workman"], "categories": ["q-bio.GN", "cs.AI"], "id": "2606.26563", "title": "scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology", "type": "arxiv", "url": "https://arxiv.org/abs/2606.26563"}, "sourceUpdatedAt": "2026-06-25T03:21:50Z", "topics": ["q-bio.GN"], "venueAttempts": [], "whyItMatters": "Existing AI-biology benchmarks measure broad knowledge or local steps; scBench-Long assesses end-to-end scientific claim production. It provides a reusable evaluation for long-horizon reasoning in single-cell data analysis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
