{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EI7IPYP4WRPYPMNEZKHEK6IZZP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aafc7925b250019a81fa4de0cacbd042480e44f66446a7f9fe5c19897bcbdcfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:59:37Z","title_canon_sha256":"1c0dc664aee1598f63e7182c03df584ecb869a02289a06342b2a1ecbde185425"},"schema_version":"1.0","source":{"id":"2508.10899","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10899","created_at":"2026-07-05T12:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10899v2","created_at":"2026-07-05T12:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10899","created_at":"2026-07-05T12:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"EI7IPYP4WRPY","created_at":"2026-07-05T12:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"EI7IPYP4WRPYPMNE","created_at":"2026-07-05T12:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"EI7IPYP4","created_at":"2026-07-05T12:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:2ad42b3fc0c96ef6492fa79ba30cbfae025c8b3314a300f8f6d172fdec0e6f62","target":"graph","created_at":"2026-07-05T12:09:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.10899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\\% of molecules proposed had high probability of being mutagenic. In this work, we introduce Medex, a dataset of priors for design problems extracted from literature describing compounds used in lab settings. It is constructed with LLM pipe","authors_text":"Cesar de la Fuente-Nunez, Haydn Thomas Jones, Jacob R. Gardner, Jiaming Liang, Jiatao Liang, Josh Magnus Ludan, Maggie Ziyu Huan, Marcelo Der Torossian Torres, Mark Yatskar, Natalie Maus, Yoseph Barash, Zachary Ives","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:59:37Z","title":"A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10899","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ddf5f4a79ac091fd6c0a2c84ba3064fd3a086dac593ebc3e4651b170783cd313","target":"record","created_at":"2026-07-05T12:09:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aafc7925b250019a81fa4de0cacbd042480e44f66446a7f9fe5c19897bcbdcfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:59:37Z","title_canon_sha256":"1c0dc664aee1598f63e7182c03df584ecb869a02289a06342b2a1ecbde185425"},"schema_version":"1.0","source":{"id":"2508.10899","kind":"arxiv","version":2}},"canonical_sha256":"223e87e1fcb45f87b1a4ca8e457919cbc659b37b3a6288e2120e2cbaa47c8845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"223e87e1fcb45f87b1a4ca8e457919cbc659b37b3a6288e2120e2cbaa47c8845","first_computed_at":"2026-07-05T12:09:45.827328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:45.827328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qz3P4PluXC6jen9ZvlrybFAgRlp7J1WfWcAFbPVXTHhCNe7+DvkWMLjm46elqlrPzBzoJLj6qFPE/kPAX0vUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:45.827797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10899","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddf5f4a79ac091fd6c0a2c84ba3064fd3a086dac593ebc3e4651b170783cd313","sha256:2ad42b3fc0c96ef6492fa79ba30cbfae025c8b3314a300f8f6d172fdec0e6f62"],"state_sha256":"6c875b5d36f4fb7f18435137c5d0db30c221377adf41ea89790a15552d0b9b4e"}