{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DGDUB3YQPWGVG7TULHSKE3Q37K","short_pith_number":"pith:DGDUB3YQ","schema_version":"1.0","canonical_sha256":"198740ef107d8d537e7459e4a26e1bfabf8cc59606e9c6d28c708d7fb56ef4a4","source":{"kind":"arxiv","id":"2412.10855","version":3},"attestation_state":"computed","paper":{"title":"Fast and Robust Visuomotor Riemannian Flow Matching Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Haoran Ding, Jan Peters, Leonel Rozo, No\\'emie Jaquier","submitted_at":"2024-12-14T15:03:33Z","abstract_excerpt":"Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to costly denoising processes or require complex sequential training arising from recent distilling approaches. This paper introduces Riemannian Flow Matching Policy (RFMP), a model that inherits the easy training and fast inference capabilities of flow matching (FM). Moreover, RFMP inherently incorporates geometric constraints commonly found in realistic robotic a"},"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":"2412.10855","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T15:03:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3af1dd15c2f269038c93bf5f5170ba9d89140120b4e440898771e55268e76e3b","abstract_canon_sha256":"002181e47fda318c814e8e4de27458e47231c0967013806d6cefedf077df0331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:20.489239Z","signature_b64":"f5YNRHbnIpzMhz08PRKcBQahUTJ3uxg+g2KNkuqi3UbQGlf3T0B8nSspcH0naXw9+6i8A2VoaGWcnD8I2kqZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"198740ef107d8d537e7459e4a26e1bfabf8cc59606e9c6d28c708d7fb56ef4a4","last_reissued_at":"2026-07-05T11:50:20.488795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:20.488795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Robust Visuomotor Riemannian Flow Matching Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Haoran Ding, Jan Peters, Leonel Rozo, No\\'emie Jaquier","submitted_at":"2024-12-14T15:03:33Z","abstract_excerpt":"Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to costly denoising processes or require complex sequential training arising from recent distilling approaches. This paper introduces Riemannian Flow Matching Policy (RFMP), a model that inherits the easy training and fast inference capabilities of flow matching (FM). Moreover, RFMP inherently incorporates geometric constraints commonly found in realistic robotic a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10855","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/2412.10855/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":"2412.10855","created_at":"2026-07-05T11:50:20.488850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10855v3","created_at":"2026-07-05T11:50:20.488850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10855","created_at":"2026-07-05T11:50:20.488850+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGDUB3YQPWGV","created_at":"2026-07-05T11:50:20.488850+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGDUB3YQPWGVG7TU","created_at":"2026-07-05T11:50:20.488850+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGDUB3YQ","created_at":"2026-07-05T11:50:20.488850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06262","citing_title":"Optimal Transport Q-Learning for Flow Policy Steering and Acceleration","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2502.07645","citing_title":"From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K","json":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K.json","graph_json":"https://pith.science/api/pith-number/DGDUB3YQPWGVG7TULHSKE3Q37K/graph.json","events_json":"https://pith.science/api/pith-number/DGDUB3YQPWGVG7TULHSKE3Q37K/events.json","paper":"https://pith.science/paper/DGDUB3YQ"},"agent_actions":{"view_html":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K","download_json":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K.json","view_paper":"https://pith.science/paper/DGDUB3YQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10855&json=true","fetch_graph":"https://pith.science/api/pith-number/DGDUB3YQPWGVG7TULHSKE3Q37K/graph.json","fetch_events":"https://pith.science/api/pith-number/DGDUB3YQPWGVG7TULHSKE3Q37K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K/action/storage_attestation","attest_author":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K/action/author_attestation","sign_citation":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K/action/citation_signature","submit_replication":"https://pith.science/pith/DGDUB3YQPWGVG7TULHSKE3Q37K/action/replication_record"}},"created_at":"2026-07-05T11:50:20.488850+00:00","updated_at":"2026-07-05T11:50:20.488850+00:00"}