{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EI7IPYP4WRPYPMNEZKHEK6IZZP","short_pith_number":"pith:EI7IPYP4","schema_version":"1.0","canonical_sha256":"223e87e1fcb45f87b1a4ca8e457919cbc659b37b3a6288e2120e2cbaa47c8845","source":{"kind":"arxiv","id":"2508.10899","version":2},"attestation_state":"computed","paper":{"title":"A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","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","submitted_at":"2025-08-14T17:59:37Z","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"},"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":"2508.10899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T17:59:37Z","cross_cats_sorted":[],"title_canon_sha256":"1c0dc664aee1598f63e7182c03df584ecb869a02289a06342b2a1ecbde185425","abstract_canon_sha256":"aafc7925b250019a81fa4de0cacbd042480e44f66446a7f9fe5c19897bcbdcfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:45.827797Z","signature_b64":"qz3P4PluXC6jen9ZvlrybFAgRlp7J1WfWcAFbPVXTHhCNe7+DvkWMLjm46elqlrPzBzoJLj6qFPE/kPAX0vUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223e87e1fcb45f87b1a4ca8e457919cbc659b37b3a6288e2120e2cbaa47c8845","last_reissued_at":"2026-07-05T12:09:45.827328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:45.827328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","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","submitted_at":"2025-08-14T17:59:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10899","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/2508.10899/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":"2508.10899","created_at":"2026-07-05T12:09:45.827382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10899v2","created_at":"2026-07-05T12:09:45.827382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10899","created_at":"2026-07-05T12:09:45.827382+00:00"},{"alias_kind":"pith_short_12","alias_value":"EI7IPYP4WRPY","created_at":"2026-07-05T12:09:45.827382+00:00"},{"alias_kind":"pith_short_16","alias_value":"EI7IPYP4WRPYPMNE","created_at":"2026-07-05T12:09:45.827382+00:00"},{"alias_kind":"pith_short_8","alias_value":"EI7IPYP4","created_at":"2026-07-05T12:09:45.827382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10912","citing_title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP","json":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP.json","graph_json":"https://pith.science/api/pith-number/EI7IPYP4WRPYPMNEZKHEK6IZZP/graph.json","events_json":"https://pith.science/api/pith-number/EI7IPYP4WRPYPMNEZKHEK6IZZP/events.json","paper":"https://pith.science/paper/EI7IPYP4"},"agent_actions":{"view_html":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP","download_json":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP.json","view_paper":"https://pith.science/paper/EI7IPYP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10899&json=true","fetch_graph":"https://pith.science/api/pith-number/EI7IPYP4WRPYPMNEZKHEK6IZZP/graph.json","fetch_events":"https://pith.science/api/pith-number/EI7IPYP4WRPYPMNEZKHEK6IZZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP/action/storage_attestation","attest_author":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP/action/author_attestation","sign_citation":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP/action/citation_signature","submit_replication":"https://pith.science/pith/EI7IPYP4WRPYPMNEZKHEK6IZZP/action/replication_record"}},"created_at":"2026-07-05T12:09:45.827382+00:00","updated_at":"2026-07-05T12:09:45.827382+00:00"}