{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4IVIKGSYRAZNMD3DSRGTOE2DJ6","short_pith_number":"pith:4IVIKGSY","schema_version":"1.0","canonical_sha256":"e22a851a588832d60f63944d3713434fbee4cb38b67f20e267a33b86c7ca28d5","source":{"kind":"arxiv","id":"2010.08687","version":3},"attestation_state":"computed","paper":{"title":"Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"David Ryan Koes, Matthew Ragoza, Tomohide Masuda","submitted_at":"2020-10-17T01:15:47Z","abstract_excerpt":"Machine learning in drug discovery has been focused on virtual screening of molecular libraries using discriminative models. Generative models are an entirely different approach that learn to represent and optimize molecules in a continuous latent space. These methods have been increasingly successful at generating two dimensional molecules as SMILES strings and molecular graphs. In this work, we describe deep generative models of three dimensional molecular structures using atomic density grids and a novel fitting algorithm for converting continuous grids to discrete molecular structures. Our"},"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":"2010.08687","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2020-10-17T01:15:47Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"37cca88858893eb20a0167ca3d29c59b680ce76a559946c856276d5502a52bd9","abstract_canon_sha256":"f8f188c400aa75f3f4d8e61f6d1ddaa3c49b3e3ece7073e7ac574f92d9c823b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:45.508420Z","signature_b64":"XDTzosX2lLgm1KAOTK6HaGXgvTuJAZP3w7NIyX1HRfIxR9kRX212YFqrZVnE5YtqgZMradvH/iXO3460q3qEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e22a851a588832d60f63944d3713434fbee4cb38b67f20e267a33b86c7ca28d5","last_reissued_at":"2026-07-05T01:51:45.507993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:45.507993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"David Ryan Koes, Matthew Ragoza, Tomohide Masuda","submitted_at":"2020-10-17T01:15:47Z","abstract_excerpt":"Machine learning in drug discovery has been focused on virtual screening of molecular libraries using discriminative models. Generative models are an entirely different approach that learn to represent and optimize molecules in a continuous latent space. These methods have been increasingly successful at generating two dimensional molecules as SMILES strings and molecular graphs. In this work, we describe deep generative models of three dimensional molecular structures using atomic density grids and a novel fitting algorithm for converting continuous grids to discrete molecular structures. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08687","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/2010.08687/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":"2010.08687","created_at":"2026-07-05T01:51:45.508050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08687v3","created_at":"2026-07-05T01:51:45.508050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08687","created_at":"2026-07-05T01:51:45.508050+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IVIKGSYRAZN","created_at":"2026-07-05T01:51:45.508050+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IVIKGSYRAZNMD3D","created_at":"2026-07-05T01:51:45.508050+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IVIKGSY","created_at":"2026-07-05T01:51:45.508050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09753","citing_title":"Do we need equivariant models for molecule generation?","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6","json":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6.json","graph_json":"https://pith.science/api/pith-number/4IVIKGSYRAZNMD3DSRGTOE2DJ6/graph.json","events_json":"https://pith.science/api/pith-number/4IVIKGSYRAZNMD3DSRGTOE2DJ6/events.json","paper":"https://pith.science/paper/4IVIKGSY"},"agent_actions":{"view_html":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6","download_json":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6.json","view_paper":"https://pith.science/paper/4IVIKGSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08687&json=true","fetch_graph":"https://pith.science/api/pith-number/4IVIKGSYRAZNMD3DSRGTOE2DJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/4IVIKGSYRAZNMD3DSRGTOE2DJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6/action/storage_attestation","attest_author":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6/action/author_attestation","sign_citation":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6/action/citation_signature","submit_replication":"https://pith.science/pith/4IVIKGSYRAZNMD3DSRGTOE2DJ6/action/replication_record"}},"created_at":"2026-07-05T01:51:45.508050+00:00","updated_at":"2026-07-05T01:51:45.508050+00:00"}