{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DVLRP5ZARWHODSGCPVWJ2GGYHP","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":"183d032fb2a149c2fdec77c716384e863ca0116d474c6b4a16dc8e4e9aacb880","cross_cats_sorted":["cs.NE","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:58:14Z","title_canon_sha256":"3b0f22d4f78f908926d79b6342cf94213293ef053f4a62a90d37ed0b98edbd22"},"schema_version":"1.0","source":{"id":"2605.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12784","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12784v2","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12784","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"DVLRP5ZARWHO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DVLRP5ZARWHODSGC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DVLRP5ZA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0bf01753fc1c3b5b34fb6cd47e8abc30f26e3d2336f731c251637f6729d9593e","target":"graph","created_at":"2026-05-18T03:09:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ToolMol achieves state-of-the-art performance on multi-objective property optimization tasks, discovering drug-like and synthesizable ligands that have >10% stronger predicted binding affinity compared to existing methods, evaluated on three protein targets. ToolMol ligands additionally achieve state-of-the-art results in gold-standard Absolute Binding Free Energy scores, gaining over existing methods by over 35%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the agentic LLM operator, when equipped with the RDKit toolbox, can consistently execute precise and unbiased ligand modifications that genuinely improve multi-objective fitness without introducing selection biases or invalid structures that undermine the genetic algorithm's search."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ToolMol pairs an LLM agent with RDKit tools inside a genetic algorithm to generate drug ligands that show stronger predicted binding than earlier methods."}],"snapshot_sha256":"5d9f3911df1532426f59d0f733b187299167d78b3a9a87964ef161e2e7710673"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approaches for molecular generation often suffer from high rates of invalid and low-quality ligand candidates, a result of the syntactic limitations of current models with regard to molecular strings. In this paper, we introduce $\\texttt{ToolMol}$, an evolutionary agentic framework for de novo drug design. $\\texttt{ToolMol}$ combines a multi-objective genetic algorithm with an agentic LLM operator that iteratively updates the ligand population. We bu","authors_text":"Andrew Y. Zhou, Michael K. Gilson, Peter Eckmann, Rose Yu, Sharvaree Vadgama, Sumanth Varambally","cross_cats":["cs.NE","q-bio.QM"],"headline":"ToolMol pairs an LLM agent with RDKit tools inside a genetic algorithm to generate drug ligands that show stronger predicted binding than earlier methods.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:58:14Z","title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery"},"references":{"count":46,"internal_anchors":5,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"10.1038/nchem.1243","is_internal_anchor":false,"ref_index":1,"title":"Quantifying the Chemical Beauty of Drugs","work_id":"c299a91c-616f-4a90-8bb6-bf819da740a4","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A., MacKnight, R., Kline, B., and Gomes, G","work_id":"93614457-269c-442f-aeec-7cd5ac2c4586","year":2023},{"cited_arxiv_id":"2304.05376","doi":"","is_internal_anchor":true,"ref_index":3,"title":"ChemCrow: Augmenting large-language models with chemistry tools","work_id":"1ceaeb05-7517-4fbd-ba9a-7a63c96b23e6","year":2023},{"cited_arxiv_id":"2602.04849","doi":"","is_internal_anchor":true,"ref_index":4,"title":"El Agente Estructural: An Artificially Intelligent Molecular Editor","work_id":"2564b567-6e74-48cc-83d4-88424f9fa307","year":2026},{"cited_arxiv_id":"","doi":"10.3389/frhem.2024.1305741","is_internal_anchor":false,"ref_index":5,"title":"A., Fernandez Prada, D","work_id":"cb7bc3b7-960d-4e36-a6a9-6bf1f128e67d","year":2024}],"snapshot_sha256":"67773c5f1f41a50b697269d2e41017e12c0a70644ab59dfd09caab470b8393e0"},"source":{"id":"2605.12784","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T04:52:05.971627Z","id":"34864f5c-dc1d-457b-b3c8-901bf5748c86","model_set":{"reader":"grok-4.3"},"one_line_summary":"ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ToolMol pairs an LLM agent with RDKit tools inside a genetic algorithm to generate drug ligands that show stronger predicted binding than earlier methods.","strongest_claim":"ToolMol achieves state-of-the-art performance on multi-objective property optimization tasks, discovering drug-like and synthesizable ligands that have >10% stronger predicted binding affinity compared to existing methods, evaluated on three protein targets. ToolMol ligands additionally achieve state-of-the-art results in gold-standard Absolute Binding Free Energy scores, gaining over existing methods by over 35%.","weakest_assumption":"The assumption that the agentic LLM operator, when equipped with the RDKit toolbox, can consistently execute precise and unbiased ligand modifications that genuinely improve multi-objective fitness without introducing selection biases or invalid structures that undermine the genetic algorithm's search."}},"verdict_id":"34864f5c-dc1d-457b-b3c8-901bf5748c86"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d855f5f733973ba92e87fe3b4ef6c1cd7666428f7e23e500a08cb3ade8f7338","target":"record","created_at":"2026-05-18T03:09:13Z","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":"183d032fb2a149c2fdec77c716384e863ca0116d474c6b4a16dc8e4e9aacb880","cross_cats_sorted":["cs.NE","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:58:14Z","title_canon_sha256":"3b0f22d4f78f908926d79b6342cf94213293ef053f4a62a90d37ed0b98edbd22"},"schema_version":"1.0","source":{"id":"2605.12784","kind":"arxiv","version":2}},"canonical_sha256":"1d5717f7208d8ee1c8c27d6c9d18d83bd93538042b7f2d81c2a46d6412419fc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d5717f7208d8ee1c8c27d6c9d18d83bd93538042b7f2d81c2a46d6412419fc3","first_computed_at":"2026-05-18T03:09:13.082995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:13.082995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDfIAiIBDpNd1A4c1clFcWztWovLQMiF6NRIZce/HBYltjF1Svl3L9eHqR67e+6snYMMDpcpGmmCpinsrdAoDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:13.083775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d855f5f733973ba92e87fe3b4ef6c1cd7666428f7e23e500a08cb3ade8f7338","sha256:0bf01753fc1c3b5b34fb6cd47e8abc30f26e3d2336f731c251637f6729d9593e"],"state_sha256":"98c4c2e4d38202cd0cd743805279a2328886a0900742c9bd1929f28a6d4c3d26"}