{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T75VDY7TVLUOXP2RVSUK2HZGOS","short_pith_number":"pith:T75VDY7T","schema_version":"1.0","canonical_sha256":"9ffb51e3f3aae8ebbf51aca8ad1f26748bcb834e36e9158a500610b5f5525277","source":{"kind":"arxiv","id":"2406.16976","version":3},"attestation_state":"computed","paper":{"title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"primary_cat":"cs.NE","authors_text":"Al\\'an Aspuru-Guzik, Chao Zhang, Chenru Duan, Cher-Tian Ser, Felix Strieth-Kalthoff, Haorui Wang, Kirill Neklyudov, Lingkai Kong, Marta Skreta, Wenhao Gao, Yanqiao Zhu, Yuanqi Du, Yuchen Zhuang, Yue Yu","submitted_at":"2024-06-23T06:22:49Z","abstract_excerpt":"Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in molecular discovery, traverse chemical space by performing random mutations and crossovers, leading to a large number of expensive objective evaluations. In this work, we ameliorate this shortcoming by incorporating chemistry-aware Large Language Models (LLMs) into EAs. Namely, we redesign crossover and mutation operations in EAs using LLMs trained o"},"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":"2406.16976","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-23T06:22:49Z","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"title_canon_sha256":"c34ad8e7b58d971fa5289d472119c641d5f097eeabe51512e92d1a35f3006757","abstract_canon_sha256":"0a9450629eb48bfbf9355969d96d0ed5b934c62c2cd31fabd36330b8e6a8588f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:04.708990Z","signature_b64":"5BAVyP5qmxg72iV0jYFe+kTj2DoHhLPRejT4R6LcPXdI0nwotmRpllxnSG7vOW7ytZwZMESW3unk82Kw2i7bCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ffb51e3f3aae8ebbf51aca8ad1f26748bcb834e36e9158a500610b5f5525277","last_reissued_at":"2026-07-05T10:26:04.708043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:04.708043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"primary_cat":"cs.NE","authors_text":"Al\\'an Aspuru-Guzik, Chao Zhang, Chenru Duan, Cher-Tian Ser, Felix Strieth-Kalthoff, Haorui Wang, Kirill Neklyudov, Lingkai Kong, Marta Skreta, Wenhao Gao, Yanqiao Zhu, Yuanqi Du, Yuchen Zhuang, Yue Yu","submitted_at":"2024-06-23T06:22:49Z","abstract_excerpt":"Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in molecular discovery, traverse chemical space by performing random mutations and crossovers, leading to a large number of expensive objective evaluations. In this work, we ameliorate this shortcoming by incorporating chemistry-aware Large Language Models (LLMs) into EAs. Namely, we redesign crossover and mutation operations in EAs using LLMs trained o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16976","kind":"arxiv","version":3},"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/2406.16976/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":"2406.16976","created_at":"2026-07-05T10:26:04.708194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16976v3","created_at":"2026-07-05T10:26:04.708194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16976","created_at":"2026-07-05T10:26:04.708194+00:00"},{"alias_kind":"pith_short_12","alias_value":"T75VDY7TVLUO","created_at":"2026-07-05T10:26:04.708194+00:00"},{"alias_kind":"pith_short_16","alias_value":"T75VDY7TVLUOXP2R","created_at":"2026-07-05T10:26:04.708194+00:00"},{"alias_kind":"pith_short_8","alias_value":"T75VDY7T","created_at":"2026-07-05T10:26:04.708194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04468","citing_title":"ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31495","citing_title":"General-purpose LLMs as Constrained Crystal Composition Generators","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02231","citing_title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10230","citing_title":"FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS","json":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS.json","graph_json":"https://pith.science/api/pith-number/T75VDY7TVLUOXP2RVSUK2HZGOS/graph.json","events_json":"https://pith.science/api/pith-number/T75VDY7TVLUOXP2RVSUK2HZGOS/events.json","paper":"https://pith.science/paper/T75VDY7T"},"agent_actions":{"view_html":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS","download_json":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS.json","view_paper":"https://pith.science/paper/T75VDY7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16976&json=true","fetch_graph":"https://pith.science/api/pith-number/T75VDY7TVLUOXP2RVSUK2HZGOS/graph.json","fetch_events":"https://pith.science/api/pith-number/T75VDY7TVLUOXP2RVSUK2HZGOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS/action/storage_attestation","attest_author":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS/action/author_attestation","sign_citation":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS/action/citation_signature","submit_replication":"https://pith.science/pith/T75VDY7TVLUOXP2RVSUK2HZGOS/action/replication_record"}},"created_at":"2026-07-05T10:26:04.708194+00:00","updated_at":"2026-07-05T10:26:04.708194+00:00"}