{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:56LCV3PMNAE7NOJ4OYYOBBKKOU","short_pith_number":"pith:56LCV3PM","schema_version":"1.0","canonical_sha256":"ef962aedec6809f6b93c7630e0854a75079b92b32a270601b2764aa25dad0107","source":{"kind":"arxiv","id":"2312.09852","version":3},"attestation_state":"computed","paper":{"title":"Learning Distributions on Manifolds with Free-Form Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Armand Rousselot, Felix Draxler, Peter Sorrenson, Sander Hummerich, Ullrich K\\\"othe","submitted_at":"2023-12-15T14:58:34Z","abstract_excerpt":"We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds. The existing approaches to learning a distribution on arbitrary manifolds are expensive at inference time, since sampling requires solving a differential equation. Our method overcomes this limitation by sampling in a single function evaluation. The key innovation is to optimize a neural network via maximum likelihood on the manifold, possible by adapting the free-form flow framework to Riemannian manifolds. M-FFF is straightforwardly adapted to any manifold with a known projection. It consistentl"},"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":"2312.09852","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-15T14:58:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e24508ed173c71fc13b08e15b3f5f8a0ecc5d0bf3020c66d1c4f1335ec91d430","abstract_canon_sha256":"cf52efa89df169225c1514f0cd279da140290d739e652edf2dc5a3db347fcac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:52.458744Z","signature_b64":"QSHXbF1MVJ5aXQb97gg6uVk+XuAMVQGJpwBhtLofRRtRG1It1pIYMJrm7YUMPyOere0IkYRlz8jL9ZVIxes2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef962aedec6809f6b93c7630e0854a75079b92b32a270601b2764aa25dad0107","last_reissued_at":"2026-07-05T09:39:52.458264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:52.458264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Distributions on Manifolds with Free-Form Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Armand Rousselot, Felix Draxler, Peter Sorrenson, Sander Hummerich, Ullrich K\\\"othe","submitted_at":"2023-12-15T14:58:34Z","abstract_excerpt":"We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds. The existing approaches to learning a distribution on arbitrary manifolds are expensive at inference time, since sampling requires solving a differential equation. Our method overcomes this limitation by sampling in a single function evaluation. The key innovation is to optimize a neural network via maximum likelihood on the manifold, possible by adapting the free-form flow framework to Riemannian manifolds. M-FFF is straightforwardly adapted to any manifold with a known projection. It consistentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09852","kind":"arxiv","version":3},"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/2312.09852/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":"2312.09852","created_at":"2026-07-05T09:39:52.458322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09852v3","created_at":"2026-07-05T09:39:52.458322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09852","created_at":"2026-07-05T09:39:52.458322+00:00"},{"alias_kind":"pith_short_12","alias_value":"56LCV3PMNAE7","created_at":"2026-07-05T09:39:52.458322+00:00"},{"alias_kind":"pith_short_16","alias_value":"56LCV3PMNAE7NOJ4","created_at":"2026-07-05T09:39:52.458322+00:00"},{"alias_kind":"pith_short_8","alias_value":"56LCV3PM","created_at":"2026-07-05T09:39:52.458322+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/56LCV3PMNAE7NOJ4OYYOBBKKOU","json":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU.json","graph_json":"https://pith.science/api/pith-number/56LCV3PMNAE7NOJ4OYYOBBKKOU/graph.json","events_json":"https://pith.science/api/pith-number/56LCV3PMNAE7NOJ4OYYOBBKKOU/events.json","paper":"https://pith.science/paper/56LCV3PM"},"agent_actions":{"view_html":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU","download_json":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU.json","view_paper":"https://pith.science/paper/56LCV3PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09852&json=true","fetch_graph":"https://pith.science/api/pith-number/56LCV3PMNAE7NOJ4OYYOBBKKOU/graph.json","fetch_events":"https://pith.science/api/pith-number/56LCV3PMNAE7NOJ4OYYOBBKKOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU/action/storage_attestation","attest_author":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU/action/author_attestation","sign_citation":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU/action/citation_signature","submit_replication":"https://pith.science/pith/56LCV3PMNAE7NOJ4OYYOBBKKOU/action/replication_record"}},"created_at":"2026-07-05T09:39:52.458322+00:00","updated_at":"2026-07-05T09:39:52.458322+00:00"}