{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C6AMKHQ3YKPO4SUOKP4EPN4ZP7","short_pith_number":"pith:C6AMKHQ3","schema_version":"1.0","canonical_sha256":"1780c51e1bc29eee4a8e53f847b7997ffd98f20c8dc6dbd7cda15f0285833ebf","source":{"kind":"arxiv","id":"1905.11600","version":1},"attestation_state":"computed","paper":{"title":"GraphNVP: An Invertible Flow Model for Generating Molecular Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Katushiko Ishiguro, Kaushalya Madhawa, Kosuke Nakago, Motoki Abe","submitted_at":"2019-05-28T04:13:23Z","abstract_excerpt":"We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows. We empirically demonstrate that our model efficiently generates valid molecular graphs with almost no duplicated molecules. In addition, we observe that the learned latent space can be used to generate molecules with desired chemical properties."},"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":"1905.11600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-28T04:13:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"07437bcae4d80a43c3dfc61e0d1c9379f40073bf76176e9c19df4d8273df868b","abstract_canon_sha256":"2bb7ac8a17423acabc2adbf5178ec7416198229f91362f1dec2ccb79133e0862"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:52.889943Z","signature_b64":"86I6KXP99EDtNkzfVtBRzhPJPoSNeG+zKfXZvHiKFWb4wB4bhNbK+pmIhK8o2BhUAcbvKtktLZA87/0aV0zPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1780c51e1bc29eee4a8e53f847b7997ffd98f20c8dc6dbd7cda15f0285833ebf","last_reissued_at":"2026-05-17T23:44:52.889444Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:52.889444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphNVP: An Invertible Flow Model for Generating Molecular Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Katushiko Ishiguro, Kaushalya Madhawa, Kosuke Nakago, Motoki Abe","submitted_at":"2019-05-28T04:13:23Z","abstract_excerpt":"We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows. We empirically demonstrate that our model efficiently generates valid molecular graphs with almost no duplicated molecules. In addition, we observe that the learned latent space can be used to generate molecules with desired chemical properties."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11600","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":"1905.11600","created_at":"2026-05-17T23:44:52.889522+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11600v1","created_at":"2026-05-17T23:44:52.889522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11600","created_at":"2026-05-17T23:44:52.889522+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6AMKHQ3YKPO","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6AMKHQ3YKPO4SUO","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6AMKHQ3","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2509.17291","citing_title":"GraphWeave: Interpretable and Robust Graph Generation via Random Walk Trajectories","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2510.20792","citing_title":"BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25732","citing_title":"Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08189","citing_title":"Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7","json":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7.json","graph_json":"https://pith.science/api/pith-number/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/graph.json","events_json":"https://pith.science/api/pith-number/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/events.json","paper":"https://pith.science/paper/C6AMKHQ3"},"agent_actions":{"view_html":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7","download_json":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7.json","view_paper":"https://pith.science/paper/C6AMKHQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11600&json=true","fetch_graph":"https://pith.science/api/pith-number/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/graph.json","fetch_events":"https://pith.science/api/pith-number/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/action/storage_attestation","attest_author":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/action/author_attestation","sign_citation":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/action/citation_signature","submit_replication":"https://pith.science/pith/C6AMKHQ3YKPO4SUOKP4EPN4ZP7/action/replication_record"}},"created_at":"2026-05-17T23:44:52.889522+00:00","updated_at":"2026-05-17T23:44:52.889522+00:00"}