{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZZWIW6ZQYDU3VO2RTCUZ7LAC4F","short_pith_number":"pith:ZZWIW6ZQ","schema_version":"1.0","canonical_sha256":"ce6c8b7b30c0e9babb5198a99fac02e165250a0eac7dadf5a85c72df5d3b465c","source":{"kind":"arxiv","id":"2209.02606","version":2},"attestation_state":"computed","paper":{"title":"Unifying Generative Models with GFlowNets and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Nikolay Malkin, Ricky T. Q. Chen, Yoshua Bengio","submitted_at":"2022-09-06T15:52:51Z","abstract_excerpt":"There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models and the recently introduced GFlowNet framework, a probabilistic inference machine which treats sampling as a decision-making process. This analysis sheds light on their overlapping traits and provides a unifying viewpoint through the lens of learning with Markovian trajectories. Our framework provides a means for unifying training and inference algorithms, and provides a route"},"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":"2209.02606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-06T15:52:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a1e2f1e21d17c74faec3c61f785745cd175186d93e28103bfae55f5d43e21251","abstract_canon_sha256":"64754a13fb4f5ec702786658c321ab4c3692d2bf959db8838795e897b906942a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:07.685229Z","signature_b64":"s7AsASRYA6l5JfElUv9Ro/nzbhLwNTk9ll0KQOkcDlIyef7pFb9FjCmDXdZoWzd3hRta4NtpOhR1UOFJQReWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce6c8b7b30c0e9babb5198a99fac02e165250a0eac7dadf5a85c72df5d3b465c","last_reissued_at":"2026-07-05T05:37:07.684734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:07.684734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Generative Models with GFlowNets and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Nikolay Malkin, Ricky T. Q. Chen, Yoshua Bengio","submitted_at":"2022-09-06T15:52:51Z","abstract_excerpt":"There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models and the recently introduced GFlowNet framework, a probabilistic inference machine which treats sampling as a decision-making process. This analysis sheds light on their overlapping traits and provides a unifying viewpoint through the lens of learning with Markovian trajectories. Our framework provides a means for unifying training and inference algorithms, and provides a route"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02606","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.02606/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":"2209.02606","created_at":"2026-07-05T05:37:07.684797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.02606v2","created_at":"2026-07-05T05:37:07.684797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02606","created_at":"2026-07-05T05:37:07.684797+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZWIW6ZQYDU3","created_at":"2026-07-05T05:37:07.684797+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZWIW6ZQYDU3VO2R","created_at":"2026-07-05T05:37:07.684797+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZWIW6ZQ","created_at":"2026-07-05T05:37:07.684797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05266","citing_title":"A Distributional Framework for Generative Modeling of Molecular Crystals","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06272","citing_title":"Your GFlowNet Secretly Learns an Optimal Transport Plan","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01729","citing_title":"Stable GFlowNets with TV Monitoring and Probabilistic Guarantees","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F","json":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F.json","graph_json":"https://pith.science/api/pith-number/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/graph.json","events_json":"https://pith.science/api/pith-number/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/events.json","paper":"https://pith.science/paper/ZZWIW6ZQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F","download_json":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F.json","view_paper":"https://pith.science/paper/ZZWIW6ZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.02606&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/action/storage_attestation","attest_author":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/action/author_attestation","sign_citation":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/action/citation_signature","submit_replication":"https://pith.science/pith/ZZWIW6ZQYDU3VO2RTCUZ7LAC4F/action/replication_record"}},"created_at":"2026-07-05T05:37:07.684797+00:00","updated_at":"2026-07-05T05:37:07.684797+00:00"}