{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7XQN5GMYH5VPKE4K4IZ3PVS43E","short_pith_number":"pith:7XQN5GMY","schema_version":"1.0","canonical_sha256":"fde0de99983f6af5138ae233b7d65cd9279dc93f06f799aaf42f69de0f829754","source":{"kind":"arxiv","id":"2606.19245","version":2},"attestation_state":"computed","paper":{"title":"TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alex Urrutia, Hannah Le, Kenny Workman, Mahsa Yazdani, Ramesh Ramasamy, Tim Proctor","submitted_at":"2026-06-17T16:23:45Z","abstract_excerpt":"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. 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. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.19245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T16:23:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aef950731b0da3d7876258025d16b5c09ebbe370de31ca324f8ca3fd8dd89608","abstract_canon_sha256":"8c5348d8a029b02cb8dbc262182ef851efe4f24d7a56ae09f4a44e067e7a248b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:22.613770Z","signature_b64":"qEClAxMP9DH1lvqrwpEjnd+gFacDocMx2I0X0kufOSZM/8YPknRqmcT4MZmdV1G9wcOsVMmOxHcWIQBbS+vMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde0de99983f6af5138ae233b7d65cd9279dc93f06f799aaf42f69de0f829754","last_reissued_at":"2026-06-19T16:12:22.613408Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:22.613408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alex Urrutia, Hannah Le, Kenny Workman, Mahsa Yazdani, Ramesh Ramasamy, Tim Proctor","submitted_at":"2026-06-17T16:23:45Z","abstract_excerpt":"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. 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. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19245","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.19245/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.19245","created_at":"2026-06-19T16:12:22.613481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19245v2","created_at":"2026-06-19T16:12:22.613481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19245","created_at":"2026-06-19T16:12:22.613481+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XQN5GMYH5VP","created_at":"2026-06-19T16:12:22.613481+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XQN5GMYH5VPKE4K","created_at":"2026-06-19T16:12:22.613481+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XQN5GMY","created_at":"2026-06-19T16:12:22.613481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E","json":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E.json","graph_json":"https://pith.science/api/pith-number/7XQN5GMYH5VPKE4K4IZ3PVS43E/graph.json","events_json":"https://pith.science/api/pith-number/7XQN5GMYH5VPKE4K4IZ3PVS43E/events.json","paper":"https://pith.science/paper/7XQN5GMY"},"agent_actions":{"view_html":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E","download_json":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E.json","view_paper":"https://pith.science/paper/7XQN5GMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19245&json=true","fetch_graph":"https://pith.science/api/pith-number/7XQN5GMYH5VPKE4K4IZ3PVS43E/graph.json","fetch_events":"https://pith.science/api/pith-number/7XQN5GMYH5VPKE4K4IZ3PVS43E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E/action/storage_attestation","attest_author":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E/action/author_attestation","sign_citation":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E/action/citation_signature","submit_replication":"https://pith.science/pith/7XQN5GMYH5VPKE4K4IZ3PVS43E/action/replication_record"}},"created_at":"2026-06-19T16:12:22.613481+00:00","updated_at":"2026-06-19T16:12:22.613481+00:00"}