{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D5ZRCHG5GZHMCRDIWMCJ7NEO4Q","short_pith_number":"pith:D5ZRCHG5","schema_version":"1.0","canonical_sha256":"1f73111cdd364ec14468b3049fb48ee43c6b05b1168b73d69f4fb2abf532e2b8","source":{"kind":"arxiv","id":"1905.13372","version":1},"attestation_state":"computed","paper":{"title":"MolecularRNN: Generating realistic molecular graphs with optimized properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.MN","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junier Oliva, Mariya Popova, Mykhailo Shvets, Olexandr Isayev","submitted_at":"2019-05-31T01:33:13Z","abstract_excerpt":"Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estim"},"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":"1905.13372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T01:33:13Z","cross_cats_sorted":["cs.AI","q-bio.MN","q-bio.QM","stat.ML"],"title_canon_sha256":"ff2944e2d470913776b109474fda089679fdc20d9e26a384d1bf874c6af107a1","abstract_canon_sha256":"27cf40b707aa6609c26448c37ec03ae1ebacfbff9becfbc92a0be8b761ca77ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.136391Z","signature_b64":"IJPu/th+3LOXCvbZUVweRBa8IOtdaUGAK+zdDYDw2tr5T6IVoeMKJk/KBmlDSEi4xancLcHFCJYmrPkMVIXLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f73111cdd364ec14468b3049fb48ee43c6b05b1168b73d69f4fb2abf532e2b8","last_reissued_at":"2026-05-17T23:44:35.135615Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.135615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolecularRNN: Generating realistic molecular graphs with optimized properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.MN","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junier Oliva, Mariya Popova, Mykhailo Shvets, Olexandr Isayev","submitted_at":"2019-05-31T01:33:13Z","abstract_excerpt":"Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13372","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":"1905.13372","created_at":"2026-05-17T23:44:35.135744+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13372v1","created_at":"2026-05-17T23:44:35.135744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13372","created_at":"2026-05-17T23:44:35.135744+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5ZRCHG5GZHM","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5ZRCHG5GZHMCRDI","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5ZRCHG5","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18031","citing_title":"How Creative Are Large Language Models in Generating Molecules?","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08189","citing_title":"Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02780","citing_title":"Fine-Grained Graph Generation through Latent Mixture Scheduling","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q","json":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q.json","graph_json":"https://pith.science/api/pith-number/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/graph.json","events_json":"https://pith.science/api/pith-number/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/events.json","paper":"https://pith.science/paper/D5ZRCHG5"},"agent_actions":{"view_html":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q","download_json":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q.json","view_paper":"https://pith.science/paper/D5ZRCHG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13372&json=true","fetch_graph":"https://pith.science/api/pith-number/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/action/storage_attestation","attest_author":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/action/author_attestation","sign_citation":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/action/citation_signature","submit_replication":"https://pith.science/pith/D5ZRCHG5GZHMCRDIWMCJ7NEO4Q/action/replication_record"}},"created_at":"2026-05-17T23:44:35.135744+00:00","updated_at":"2026-05-17T23:44:35.135744+00:00"}