{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JDPBQ5LZTAGAM3Q4M3CL57WYHM","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":"31d9fa13d148469f0fd904453a4257633d3fb07db2aa48deec673790f862734b","cross_cats_sorted":["cs.NE","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:51:33Z","title_canon_sha256":"f2a79486049c83c347619c8ab39ab93015ce2103b81c58ab0e12cd0aa696a0e0"},"schema_version":"1.0","source":{"id":"2407.18897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18897","created_at":"2026-07-05T08:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18897v1","created_at":"2026-07-05T08:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18897","created_at":"2026-07-05T08:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"JDPBQ5LZTAGA","created_at":"2026-07-05T08:48:56Z"},{"alias_kind":"pith_short_16","alias_value":"JDPBQ5LZTAGAM3Q4","created_at":"2026-07-05T08:48:56Z"},{"alias_kind":"pith_short_8","alias_value":"JDPBQ5LZ","created_at":"2026-07-05T08:48:56Z"}],"graph_snapshots":[{"event_id":"sha256:9216c9a442081cce484444e6504e625c2d2a6602f4241ee794fede7289238ec8","target":"graph","created_at":"2026-07-05T08:48:56Z","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/2407.18897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models have opened new possibilities for generative molecular drug design. We present Chemlactica and Chemma, two language models fine-tuned on a novel corpus of 110M molecules with computed properties, totaling 40B tokens. These models demonstrate strong performance in generating molecules with specified properties and predicting new molecular characteristics from limited samples. We introduce a novel optimization algorithm that leverages our language models to optimize molecules for arbitrary properties given limited access to a black box oracle. Our app","authors_text":"Armen Aghajanyan, Gayane Chilingaryan, Hrant Khachatrian, Menua Bedrosian, Philipp Guevorguian, Tigran Fahradyan","cross_cats":["cs.NE","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:51:33Z","title":"Small Molecule Optimization with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18897","kind":"arxiv","version":1},"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":"sha256:2f00b1534174baab77fa5c84821a1a8325de450700ed347d9ac849ea68f6512f","target":"record","created_at":"2026-07-05T08:48:56Z","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":"31d9fa13d148469f0fd904453a4257633d3fb07db2aa48deec673790f862734b","cross_cats_sorted":["cs.NE","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:51:33Z","title_canon_sha256":"f2a79486049c83c347619c8ab39ab93015ce2103b81c58ab0e12cd0aa696a0e0"},"schema_version":"1.0","source":{"id":"2407.18897","kind":"arxiv","version":1}},"canonical_sha256":"48de187579980c066e1c66c4befed83b1bd4f4a1b7fc8a950180e3818d8db143","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48de187579980c066e1c66c4befed83b1bd4f4a1b7fc8a950180e3818d8db143","first_computed_at":"2026-07-05T08:48:56.026519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:56.026519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6L3JfGxJGmDACjCy5r63951Xk59UEAnOpshgkLxq/67H2CzF1TnHTP0QaNN7vyAM9QnZbjgjqVeEI91j+9v5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:56.027015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f00b1534174baab77fa5c84821a1a8325de450700ed347d9ac849ea68f6512f","sha256:9216c9a442081cce484444e6504e625c2d2a6602f4241ee794fede7289238ec8"],"state_sha256":"a74f655e1dcc7c2872f11a15bca4b7d83770017551ee317217e72e191a5666bc"}