{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4IANPSRGF5M5O3YWC4O5FUJ7WN","short_pith_number":"pith:4IANPSRG","schema_version":"1.0","canonical_sha256":"e200d7ca262f59d76f16171dd2d13fb377165f3f801ccb7715c6ce7a18108b52","source":{"kind":"arxiv","id":"2605.31106","version":1},"attestation_state":"computed","paper":{"title":"Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gyeonghoon Ko, Juho Lee","submitted_at":"2026-05-29T10:16:47Z","abstract_excerpt":"Riemannian diffusion models generalize score-based generative modeling to manifold-supported data via stochastic diffusion equations on the manifold. However, training requires sampling from and differentiating the manifold heat kernel, which is rarely available in closed form beyond a few highly symmetric manifolds. We propose a general approach that approximates the heat kernel by directly solving the manifold heat equation with a physics-informed neural network (PINN). Given an explicit manifold specification, we choose a coordinate system, derive the corresponding heat (Fokker--Planck) equ"},"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":"2605.31106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T10:16:47Z","cross_cats_sorted":[],"title_canon_sha256":"f548d7eebd9530f6b31597ed63c741a520be16de9df7117a98dd6f3136549b2e","abstract_canon_sha256":"96ad42ccdd330518f2b2fde2832f041246ce3df16438553cd4ad8291450a5218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:58.265769Z","signature_b64":"/CwcUFITAW6IUDL9YxUpkMoWhKoPacP774vSOBCuwIEbRZ9YK4IT/kXnC+c8CcpZ+b0ypg/0K6g7lwXpeDBWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e200d7ca262f59d76f16171dd2d13fb377165f3f801ccb7715c6ce7a18108b52","last_reissued_at":"2026-06-01T01:03:58.264793Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:58.264793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gyeonghoon Ko, Juho Lee","submitted_at":"2026-05-29T10:16:47Z","abstract_excerpt":"Riemannian diffusion models generalize score-based generative modeling to manifold-supported data via stochastic diffusion equations on the manifold. However, training requires sampling from and differentiating the manifold heat kernel, which is rarely available in closed form beyond a few highly symmetric manifolds. We propose a general approach that approximates the heat kernel by directly solving the manifold heat equation with a physics-informed neural network (PINN). Given an explicit manifold specification, we choose a coordinate system, derive the corresponding heat (Fokker--Planck) equ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31106","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/2605.31106/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":"2605.31106","created_at":"2026-06-01T01:03:58.264960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31106v1","created_at":"2026-06-01T01:03:58.264960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31106","created_at":"2026-06-01T01:03:58.264960+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IANPSRGF5M5","created_at":"2026-06-01T01:03:58.264960+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IANPSRGF5M5O3YW","created_at":"2026-06-01T01:03:58.264960+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IANPSRG","created_at":"2026-06-01T01:03:58.264960+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/4IANPSRGF5M5O3YWC4O5FUJ7WN","json":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN.json","graph_json":"https://pith.science/api/pith-number/4IANPSRGF5M5O3YWC4O5FUJ7WN/graph.json","events_json":"https://pith.science/api/pith-number/4IANPSRGF5M5O3YWC4O5FUJ7WN/events.json","paper":"https://pith.science/paper/4IANPSRG"},"agent_actions":{"view_html":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN","download_json":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN.json","view_paper":"https://pith.science/paper/4IANPSRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31106&json=true","fetch_graph":"https://pith.science/api/pith-number/4IANPSRGF5M5O3YWC4O5FUJ7WN/graph.json","fetch_events":"https://pith.science/api/pith-number/4IANPSRGF5M5O3YWC4O5FUJ7WN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN/action/storage_attestation","attest_author":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN/action/author_attestation","sign_citation":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN/action/citation_signature","submit_replication":"https://pith.science/pith/4IANPSRGF5M5O3YWC4O5FUJ7WN/action/replication_record"}},"created_at":"2026-06-01T01:03:58.264960+00:00","updated_at":"2026-06-01T01:03:58.264960+00:00"}