{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DOXWWCYFG4KGJMWXQPYKUCRVZD","short_pith_number":"pith:DOXWWCYF","schema_version":"1.0","canonical_sha256":"1baf6b0b05371464b2d783f0aa0a35c8e75d273d91bce003b4f0102e3f42f6cb","source":{"kind":"arxiv","id":"1811.11222","version":1},"attestation_state":"computed","paper":{"title":"Grammars and reinforcement learning for molecule optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Egor Kraev","submitted_at":"2018-11-27T19:48:02Z","abstract_excerpt":"We seek to automate the design of molecules based on specific chemical properties. Our primary contributions are a simpler method for generating SMILES strings guaranteed to be chemically valid, using a combination of a new context-free grammar for SMILES and additional masking logic; and casting the molecular property optimization as a reinforcement learning problem, specifically best-of-batch policy gradient applied to a Transformer model architecture. This approach uses substantially fewer model steps per atom than earlier approaches, thus enabling generation of larger molecules, and beats "},"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":"1811.11222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T19:48:02Z","cross_cats_sorted":["physics.chem-ph","stat.ML"],"title_canon_sha256":"ed7ec34e1557f8e350803146a9705998b41a43142a90ed1e2607e4dc7541077e","abstract_canon_sha256":"8ec51ac9529aa25b0e40be8c0c3bcc162a34786cb11092b19f7f9bd0be1238b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:44.445887Z","signature_b64":"h+WY2X3K+LdG1UYycSdliGw8jojQBE48xc7aETW7/RM1mxef4ZMiBtsDCgyV9VJg2HWcYDKJaM2wgbBzBpicBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1baf6b0b05371464b2d783f0aa0a35c8e75d273d91bce003b4f0102e3f42f6cb","last_reissued_at":"2026-05-17T23:59:44.445478Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:44.445478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grammars and reinforcement learning for molecule optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Egor Kraev","submitted_at":"2018-11-27T19:48:02Z","abstract_excerpt":"We seek to automate the design of molecules based on specific chemical properties. Our primary contributions are a simpler method for generating SMILES strings guaranteed to be chemically valid, using a combination of a new context-free grammar for SMILES and additional masking logic; and casting the molecular property optimization as a reinforcement learning problem, specifically best-of-batch policy gradient applied to a Transformer model architecture. This approach uses substantially fewer model steps per atom than earlier approaches, thus enabling generation of larger molecules, and beats "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11222","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1811.11222","created_at":"2026-05-17T23:59:44.445536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11222v1","created_at":"2026-05-17T23:59:44.445536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11222","created_at":"2026-05-17T23:59:44.445536+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOXWWCYFG4KG","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOXWWCYFG4KGJMWX","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOXWWCYF","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD","json":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD.json","graph_json":"https://pith.science/api/pith-number/DOXWWCYFG4KGJMWXQPYKUCRVZD/graph.json","events_json":"https://pith.science/api/pith-number/DOXWWCYFG4KGJMWXQPYKUCRVZD/events.json","paper":"https://pith.science/paper/DOXWWCYF"},"agent_actions":{"view_html":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD","download_json":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD.json","view_paper":"https://pith.science/paper/DOXWWCYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11222&json=true","fetch_graph":"https://pith.science/api/pith-number/DOXWWCYFG4KGJMWXQPYKUCRVZD/graph.json","fetch_events":"https://pith.science/api/pith-number/DOXWWCYFG4KGJMWXQPYKUCRVZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD/action/storage_attestation","attest_author":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD/action/author_attestation","sign_citation":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD/action/citation_signature","submit_replication":"https://pith.science/pith/DOXWWCYFG4KGJMWXQPYKUCRVZD/action/replication_record"}},"created_at":"2026-05-17T23:59:44.445536+00:00","updated_at":"2026-05-17T23:59:44.445536+00:00"}