{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6GNSWTBUFHR7JSYCXBSRKRTFLD","short_pith_number":"pith:6GNSWTBU","schema_version":"1.0","canonical_sha256":"f19b2b4c3429e3f4cb02b86515466558fdcfc279f2d7e52470d2cdd8cb876b55","source":{"kind":"arxiv","id":"2210.04296","version":4},"attestation_state":"computed","paper":{"title":"FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2022-10-09T16:27:25Z","abstract_excerpt":"Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the Fokker-Planck equation (FPE), a partial differential equation (PDE) governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation called the score FPE that characterizes the noise-conditional scores of the perturbed data densities (i.e., their gradients). Surprisingly, despite the impressive e"},"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":"2210.04296","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-09T16:27:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"239f0f678e29452d5a714f0b9a32cccd3aa90b2c8764be4c97411063e58e3455","abstract_canon_sha256":"1a83f789ffe2caec93b6c6269d92b915dbb3bea2b90b429ee327b48f78085e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:37.212232Z","signature_b64":"Uvm87cO1ntEm+idfE/Lxcay5WalM/8TOb7yoTRTKgPCjJaSmJ6OrROyeBNbMUMEn86YiRote4yn7TPz6kmLYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f19b2b4c3429e3f4cb02b86515466558fdcfc279f2d7e52470d2cdd8cb876b55","last_reissued_at":"2026-07-05T06:20:37.211754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:37.211754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2022-10-09T16:27:25Z","abstract_excerpt":"Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the Fokker-Planck equation (FPE), a partial differential equation (PDE) governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation called the score FPE that characterizes the noise-conditional scores of the perturbed data densities (i.e., their gradients). Surprisingly, despite the impressive e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04296","kind":"arxiv","version":4},"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/2210.04296/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":"2210.04296","created_at":"2026-07-05T06:20:37.211815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04296v4","created_at":"2026-07-05T06:20:37.211815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04296","created_at":"2026-07-05T06:20:37.211815+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GNSWTBUFHR7","created_at":"2026-07-05T06:20:37.211815+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GNSWTBUFHR7JSYC","created_at":"2026-07-05T06:20:37.211815+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GNSWTBU","created_at":"2026-07-05T06:20:37.211815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22338","citing_title":"Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD","json":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD.json","graph_json":"https://pith.science/api/pith-number/6GNSWTBUFHR7JSYCXBSRKRTFLD/graph.json","events_json":"https://pith.science/api/pith-number/6GNSWTBUFHR7JSYCXBSRKRTFLD/events.json","paper":"https://pith.science/paper/6GNSWTBU"},"agent_actions":{"view_html":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD","download_json":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD.json","view_paper":"https://pith.science/paper/6GNSWTBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04296&json=true","fetch_graph":"https://pith.science/api/pith-number/6GNSWTBUFHR7JSYCXBSRKRTFLD/graph.json","fetch_events":"https://pith.science/api/pith-number/6GNSWTBUFHR7JSYCXBSRKRTFLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD/action/storage_attestation","attest_author":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD/action/author_attestation","sign_citation":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD/action/citation_signature","submit_replication":"https://pith.science/pith/6GNSWTBUFHR7JSYCXBSRKRTFLD/action/replication_record"}},"created_at":"2026-07-05T06:20:37.211815+00:00","updated_at":"2026-07-05T06:20:37.211815+00:00"}