{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04262", "kind": "paper", "url": "https://arxiv.org/abs/2606.04262"}], "authors": ["Maroof Kousar", "Jinsung Han", "Mohit Chandra", "Munmun De Choudhury", "Yibo Hu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04262", "source_url": "https://arxiv.org/abs/2606.04262"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.CL"], "description": {"en": "DOSEBENCH evaluates LLM decision-making on over-the-counter dosing questions, with 81 curated scenarios for adult acetaminophen and ibuprofen use. Correct answers require tracking dose timing, computing rolling 24-hour intake, and following product-label constraints."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04262", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04262", "title": "DOSEBENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Illinois Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.04262", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.04262", "source_url": "https://openalex.org/W7163562007"}, "key": "claire-radar:2606.04262", "modality": null, "name": "DOSEBENCH", "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": "unknown", "origin_record_id": "bm_dosebench_cf8cdec2", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "1bd9261b6b1e1b1543e7a37639fb4012bc892364136a8dd60fc2ce6b053f1382", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04262"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04262", "source_url": "https://arxiv.org/abs/2606.04262"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04262", "source": "claire_radar", "source_benchmark_id": "2606.04262", "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/2606.04262", "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": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "35cb50ac28ed5751da38f6dc540086da39e58e9b4641d5d407186162205a041d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DOSEBENCH evaluates LLM decision-making on over-the-counter dosing questions, with 81 curated scenarios for adult acetaminophen and ibuprofen use. Correct answers require tracking dose timing, computing rolling 24-hour intake, and following product-label constraints.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "We introduce DOSEBENCH, a focused benchmark of 81 curated OTC dosing scenarios focused on adult acetaminophen and ibuprofen use, with manually annotated gold references."}, "familyId": "bmf_828ba2bfddf1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_dosebench_cf8cdec2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.04262", "paper": "https://arxiv.org/abs/2606.04262", "pdf": "https://arxiv.org/pdf/2606.04262", "project": null, "report": "https://arxiv.org/abs/2606.04262"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the-counter (OTC) medication.", "name": "DOSEBENCH", "oneLine": "DOSEBENCH evaluates LLM decision-making on over-the-counter dosing questions, with 81 curated scenarios for adult acetaminophen and ibuprofen use. Correct answers require tracking dose timing, computing rolling 24-hour intake, and following product-label constraints.", "paperTitle": "Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.04262", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Maroof Kousar and Yibo Hu"], "categories": ["cs.CL", "cs.AI"], "id": "2606.04262", "title": "Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04262"}, "sourceUpdatedAt": "2026-06-02T22:30:15Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses an underexplored safety-relevant medical QA setting. Evaluates temporal reasoning, constraint following, and uncertainty handling, showing that confident responses can violate dosing constraints."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
