{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V4BNFWEN7GQRSCLMRBNTF2IMJC","short_pith_number":"pith:V4BNFWEN","schema_version":"1.0","canonical_sha256":"af02d2d88df9a119096c885b32e90c488924b9d46d114676b8d6c9a4ab96a6c1","source":{"kind":"arxiv","id":"1805.09076","version":2},"attestation_state":"computed","paper":{"title":"Constrained Graph Variational Autoencoders for Molecule Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander L. Gaunt, Marc Brockschmidt, Miltiadis Allamanis, Qi Liu","submitted_at":"2018-05-23T12:01:44Z","abstract_excerpt":"Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution observed in training data. We propose a variational autoencoder model in which both encoder and decoder are graph-structured. Our decoder assumes a sequential ordering of graph extension steps and we discuss and analyze design choices that mitigate the potential downsides of this linearization. Experiments compare our approach with a wide range of baselines 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":"1805.09076","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T12:01:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"99ecb8ad2d67c1ba997c4df7ec5733b31c41183c04faac0600b306ea8d0c855d","abstract_canon_sha256":"674872dbc527ff3402228bbd17713d15b7cbe1fb971fbe57d6dea29ed597b007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.557236Z","signature_b64":"zoCFCK1loN3DxG2NF7b1ENTnOw8/zVw05Ji5UIH2c554+62QWd5jbyxRE/cIPULzPNXtRPluCZ3a2U/8+k3aDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af02d2d88df9a119096c885b32e90c488924b9d46d114676b8d6c9a4ab96a6c1","last_reissued_at":"2026-05-17T23:51:54.556058Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.556058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Graph Variational Autoencoders for Molecule Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander L. Gaunt, Marc Brockschmidt, Miltiadis Allamanis, Qi Liu","submitted_at":"2018-05-23T12:01:44Z","abstract_excerpt":"Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution observed in training data. We propose a variational autoencoder model in which both encoder and decoder are graph-structured. Our decoder assumes a sequential ordering of graph extension steps and we discuss and analyze design choices that mitigate the potential downsides of this linearization. Experiments compare our approach with a wide range of baselines o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09076","kind":"arxiv","version":2},"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":"1805.09076","created_at":"2026-05-17T23:51:54.556781+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09076v2","created_at":"2026-05-17T23:51:54.556781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09076","created_at":"2026-05-17T23:51:54.556781+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4BNFWEN7GQR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4BNFWEN7GQRSCLM","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4BNFWEN","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08189","citing_title":"Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC","json":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC.json","graph_json":"https://pith.science/api/pith-number/V4BNFWEN7GQRSCLMRBNTF2IMJC/graph.json","events_json":"https://pith.science/api/pith-number/V4BNFWEN7GQRSCLMRBNTF2IMJC/events.json","paper":"https://pith.science/paper/V4BNFWEN"},"agent_actions":{"view_html":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC","download_json":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC.json","view_paper":"https://pith.science/paper/V4BNFWEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09076&json=true","fetch_graph":"https://pith.science/api/pith-number/V4BNFWEN7GQRSCLMRBNTF2IMJC/graph.json","fetch_events":"https://pith.science/api/pith-number/V4BNFWEN7GQRSCLMRBNTF2IMJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC/action/storage_attestation","attest_author":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC/action/author_attestation","sign_citation":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC/action/citation_signature","submit_replication":"https://pith.science/pith/V4BNFWEN7GQRSCLMRBNTF2IMJC/action/replication_record"}},"created_at":"2026-05-17T23:51:54.556781+00:00","updated_at":"2026-05-17T23:51:54.556781+00:00"}