{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3MYCDB5IYZ3QMBNB26SBCURQN","short_pith_number":"pith:P3MYCDB5","schema_version":"1.0","canonical_sha256":"7ed9810c3d4633b8302d0ebd208a918362c48590ef0673ad9edb5f0a41f9c826","source":{"kind":"arxiv","id":"2603.18907","version":2},"attestation_state":"computed","paper":{"title":"Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Fabio Nobile, Riccardo Saporiti","submitted_at":"2026-03-19T13:43:18Z","abstract_excerpt":"We propose a new Neural Galerkin Normalizing Flow framework to approximate the transition probability density function of a diffusion process by solving the corresponding Fokker-Planck equation with an atomic initial distribution, parametrically with respect to the location of the initial mass. By using Normalizing Flows, we look for the solution as a transformation of the transition probability density function of a reference stochastic process, ensuring that our approximation is structure-preserving and automatically satisfies positivity and mass conservation constraints. By extending Neural"},"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":"2603.18907","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T13:43:18Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"11b9a887bc840cdeabc76cf837851692cddf5173ec1798fd36b61ec193414989","abstract_canon_sha256":"b3476af3c3f68b2f19ca85bb5c5ffff8ab873a1ead0dd6aff4e628403621d28b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:37.179652Z","signature_b64":"xsf5EHSgZZfvOUHw9mYx6Je1sSM+/bYc8VZKwLHM3krnaCFOW7W9mudtN9BvO7GmPd7QnSi7VloQXDcpcOs9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed9810c3d4633b8302d0ebd208a918362c48590ef0673ad9edb5f0a41f9c826","last_reissued_at":"2026-06-30T01:17:37.178908Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:37.178908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Fabio Nobile, Riccardo Saporiti","submitted_at":"2026-03-19T13:43:18Z","abstract_excerpt":"We propose a new Neural Galerkin Normalizing Flow framework to approximate the transition probability density function of a diffusion process by solving the corresponding Fokker-Planck equation with an atomic initial distribution, parametrically with respect to the location of the initial mass. By using Normalizing Flows, we look for the solution as a transformation of the transition probability density function of a reference stochastic process, ensuring that our approximation is structure-preserving and automatically satisfies positivity and mass conservation constraints. By extending Neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.18907","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/2603.18907/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":"2603.18907","created_at":"2026-06-30T01:17:37.178998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.18907v2","created_at":"2026-06-30T01:17:37.178998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.18907","created_at":"2026-06-30T01:17:37.178998+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3MYCDB5IYZ3","created_at":"2026-06-30T01:17:37.178998+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3MYCDB5IYZ3QMBN","created_at":"2026-06-30T01:17:37.178998+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3MYCDB5","created_at":"2026-06-30T01:17:37.178998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.09434","citing_title":"A transition-density-based operator learning method for Fokker-Planck equations with various initial conditions","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04324","citing_title":"Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN","json":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN.json","graph_json":"https://pith.science/api/pith-number/P3MYCDB5IYZ3QMBNB26SBCURQN/graph.json","events_json":"https://pith.science/api/pith-number/P3MYCDB5IYZ3QMBNB26SBCURQN/events.json","paper":"https://pith.science/paper/P3MYCDB5"},"agent_actions":{"view_html":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN","download_json":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN.json","view_paper":"https://pith.science/paper/P3MYCDB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.18907&json=true","fetch_graph":"https://pith.science/api/pith-number/P3MYCDB5IYZ3QMBNB26SBCURQN/graph.json","fetch_events":"https://pith.science/api/pith-number/P3MYCDB5IYZ3QMBNB26SBCURQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN/action/storage_attestation","attest_author":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN/action/author_attestation","sign_citation":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN/action/citation_signature","submit_replication":"https://pith.science/pith/P3MYCDB5IYZ3QMBNB26SBCURQN/action/replication_record"}},"created_at":"2026-06-30T01:17:37.178998+00:00","updated_at":"2026-06-30T01:17:37.178998+00:00"}