{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X4I7ZBHN5MTSXGO74NUMSUIL74","short_pith_number":"pith:X4I7ZBHN","schema_version":"1.0","canonical_sha256":"bf11fc84edeb272b99dfe368c9510bff271e0f1f93f6790608dc8aff3ceb4692","source":{"kind":"arxiv","id":"2310.20030","version":1},"attestation_state":"computed","paper":{"title":"Scaling Riemannian Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DG","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Lou, Minkai Xu, Stefano Ermon","submitted_at":"2023-10-30T21:27:53Z","abstract_excerpt":"Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible in closed form, so prior methods resort to imprecise approximations of the score matching training objective that degrade performance and preclude applications in high dimensions. In this work, we reexamine these approximations and propose several practical improvements. Our key observation is that most relevant manifolds are symmetric spaces, which are much"},"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":"2310.20030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T21:27:53Z","cross_cats_sorted":["math.DG","stat.ML"],"title_canon_sha256":"853b595212c121ae874f17ae9530d14f71a32dac8c138e50c64b3c18cf13e5df","abstract_canon_sha256":"088ef3a3ee19adaab5eaed2fcf693a8687b4787e39715b62496ccc2b9bbadebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:22.843383Z","signature_b64":"//uQJSlZntJkMo/Op5vn5Zz9qYEJ9bv2ACG1EiNURplUa9FIOffJ+PWkVWJUe4DVohhdZXLkMtGwh+kE2gKEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf11fc84edeb272b99dfe368c9510bff271e0f1f93f6790608dc8aff3ceb4692","last_reissued_at":"2026-07-05T07:07:22.842975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:22.842975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Riemannian Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DG","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Lou, Minkai Xu, Stefano Ermon","submitted_at":"2023-10-30T21:27:53Z","abstract_excerpt":"Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible in closed form, so prior methods resort to imprecise approximations of the score matching training objective that degrade performance and preclude applications in high dimensions. In this work, we reexamine these approximations and propose several practical improvements. Our key observation is that most relevant manifolds are symmetric spaces, which are much"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20030","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/2310.20030/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":"2310.20030","created_at":"2026-07-05T07:07:22.843029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20030v1","created_at":"2026-07-05T07:07:22.843029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20030","created_at":"2026-07-05T07:07:22.843029+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4I7ZBHN5MTS","created_at":"2026-07-05T07:07:22.843029+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4I7ZBHN5MTSXGO7","created_at":"2026-07-05T07:07:22.843029+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4I7ZBHN","created_at":"2026-07-05T07:07:22.843029+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/X4I7ZBHN5MTSXGO74NUMSUIL74","json":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74.json","graph_json":"https://pith.science/api/pith-number/X4I7ZBHN5MTSXGO74NUMSUIL74/graph.json","events_json":"https://pith.science/api/pith-number/X4I7ZBHN5MTSXGO74NUMSUIL74/events.json","paper":"https://pith.science/paper/X4I7ZBHN"},"agent_actions":{"view_html":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74","download_json":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74.json","view_paper":"https://pith.science/paper/X4I7ZBHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20030&json=true","fetch_graph":"https://pith.science/api/pith-number/X4I7ZBHN5MTSXGO74NUMSUIL74/graph.json","fetch_events":"https://pith.science/api/pith-number/X4I7ZBHN5MTSXGO74NUMSUIL74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74/action/storage_attestation","attest_author":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74/action/author_attestation","sign_citation":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74/action/citation_signature","submit_replication":"https://pith.science/pith/X4I7ZBHN5MTSXGO74NUMSUIL74/action/replication_record"}},"created_at":"2026-07-05T07:07:22.843029+00:00","updated_at":"2026-07-05T07:07:22.843029+00:00"}