{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.19245", "kind": "paper", "url": "https://arxiv.org/abs/2606.19245"}], "authors": ["Hannah Le", "Ramesh Ramasamy", "Alex Urrutia", "Mahsa Yazdani", "Tim Proctor", "Kenny Workman"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.19245", "source_url": "https://arxiv.org/abs/2606.19245"}, "categories": ["Agents", "Language & Knowledge", "Materials & Chemistry"], "description": {"en": "TxBench-PP evaluates AI agents on small-molecule preclinical pharmacology tasks including mechanism-of-action, pharmacodynamics, and safety reasoning, using realistic workflow snapshots and deterministic scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.19245", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.19245", "title": "TherapeuticsBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.19245", "modality": null, "name": "TherapeuticsBench", "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_therapeuticsbench_0f53fc28", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "20ab1aeb6532e632b9dfdd005f758468b62e291be8dd41e26981ff8671d63d00", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.19245"}, "publisher": null, "released": "2026-06-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.19245", "source_url": "https://arxiv.org/abs/2606.19245"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-19245", "source": "claire_radar", "source_benchmark_id": "2606.19245", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Materials & Chemistry"], "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/2606.19245", "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": "5cb027a680373e4904e23518118872d33a37a614d7309b0be9862ec985e40b8b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TxBench-PP evaluates AI agents on small-molecule preclinical pharmacology tasks including mechanism-of-action, pharmacodynamics, and safety reasoning, using realistic workflow snapshots and deterministic scoring.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities."}, "familyId": "bmf_d3ec29543e47", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_therapeuticsbench_0f53fc28", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Materials & Chemicals"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.19245", "paper": "https://arxiv.org/abs/2606.19245", "pdf": "https://arxiv.org/pdf/2606.19245", "project": null, "report": "https://arxiv.org/abs/2606.19245"}, "metrics": [], "motivation": "Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions.", "name": "TherapeuticsBench", "oneLine": "TxBench-PP evaluates AI agents on small-molecule preclinical pharmacology tasks including mechanism-of-action, pharmacodynamics, and safety reasoning, using realistic workflow snapshots and deterministic scoring.", "paperTitle": "TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology", "primaryDomain": "Materials & Chemistry", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.19245", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.19245"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-17", "source": {"authors": ["Hannah Le", "Ramesh Ramasamy", "Alex Urrutia", "Mahsa Yazdani", "Tim Proctor", "Kenny Workman"], "categories": ["cs.AI", "cs.LG"], "id": "2606.19245", "title": "TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology", "type": "arxiv", "url": "https://arxiv.org/abs/2606.19245"}, "sourceUpdatedAt": "2026-06-18T02:34:51Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Provides verifiable evaluation of agents on realistic drug discovery decisions, addressing the need for trusted benchmarks in high-stakes scientific applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
