{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VACIS7VSAH7AHY4JAYXOTOIJ6","short_pith_number":"pith:3VACIS7V","schema_version":"1.0","canonical_sha256":"dd40244bf5900ff01f1c4831774dc84f8584436ece1ebf4202a0bc725a6e0aa7","source":{"kind":"arxiv","id":"2407.15238","version":1},"attestation_state":"computed","paper":{"title":"Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arghya Pal, Chee-Ming Ting, Junn Yong Loo, Michelle Adeline, Raphael C.-W. Phan, Vishnu Monn Baskaran","submitted_at":"2024-07-21T18:08:12Z","abstract_excerpt":"Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence training. In this paper, we present a novel energy-based generative framework, Variational Potential Flow (VAPO), that entirely dispenses with implicit MCMC sampling and does not rely on complementary latent models or cooperative training. The VAPO framework aims to learn a potential energy function whose gradient (flow) guides the prior samples, so th"},"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":"2407.15238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-21T18:08:12Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"76116d13493b064b685a0b527f8927341e35ad0a27be43b29d6498509a8a0ed4","abstract_canon_sha256":"7d145edcfccb439ae131f4fb6ea6105a313e304229aa84a89da71bd26c9f26a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:40.623185Z","signature_b64":"kUOkOp8KwuS8dH33hJnxYlBgjWjV7/Q/77hRoM4b63TVnIj4HQoW/fPXCTqy8acLH+Kxt0xQ1Fr9XpjWmz9dCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd40244bf5900ff01f1c4831774dc84f8584436ece1ebf4202a0bc725a6e0aa7","last_reissued_at":"2026-07-05T08:46:40.622675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:40.622675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arghya Pal, Chee-Ming Ting, Junn Yong Loo, Michelle Adeline, Raphael C.-W. Phan, Vishnu Monn Baskaran","submitted_at":"2024-07-21T18:08:12Z","abstract_excerpt":"Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence training. In this paper, we present a novel energy-based generative framework, Variational Potential Flow (VAPO), that entirely dispenses with implicit MCMC sampling and does not rely on complementary latent models or cooperative training. The VAPO framework aims to learn a potential energy function whose gradient (flow) guides the prior samples, so th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15238","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.15238/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":"2407.15238","created_at":"2026-07-05T08:46:40.622746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15238v1","created_at":"2026-07-05T08:46:40.622746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15238","created_at":"2026-07-05T08:46:40.622746+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VACIS7VSAH7","created_at":"2026-07-05T08:46:40.622746+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VACIS7VSAH7AHY4","created_at":"2026-07-05T08:46:40.622746+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VACIS7V","created_at":"2026-07-05T08:46:40.622746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6","json":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6.json","graph_json":"https://pith.science/api/pith-number/3VACIS7VSAH7AHY4JAYXOTOIJ6/graph.json","events_json":"https://pith.science/api/pith-number/3VACIS7VSAH7AHY4JAYXOTOIJ6/events.json","paper":"https://pith.science/paper/3VACIS7V"},"agent_actions":{"view_html":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6","download_json":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6.json","view_paper":"https://pith.science/paper/3VACIS7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15238&json=true","fetch_graph":"https://pith.science/api/pith-number/3VACIS7VSAH7AHY4JAYXOTOIJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/3VACIS7VSAH7AHY4JAYXOTOIJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6/action/storage_attestation","attest_author":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6/action/author_attestation","sign_citation":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6/action/citation_signature","submit_replication":"https://pith.science/pith/3VACIS7VSAH7AHY4JAYXOTOIJ6/action/replication_record"}},"created_at":"2026-07-05T08:46:40.622746+00:00","updated_at":"2026-07-05T08:46:40.622746+00:00"}