{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:557LMOBNQXPPVDEZDRED6XISAS","short_pith_number":"pith:557LMOBN","schema_version":"1.0","canonical_sha256":"ef7eb6382d85defa8c991c483f5d12049cc1a61426d53169f91895501355d628","source":{"kind":"arxiv","id":"2302.03660","version":3},"attestation_state":"computed","paper":{"title":"Flow Matching on General Geometries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ricky T. Q. Chen, Yaron Lipman","submitted_at":"2023-02-07T18:21:24Z","abstract_excerpt":"We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training continuous normalizing flows on manifolds. Existing methods for generative modeling on manifolds either require expensive simulation, are inherently unable to scale to high dimensions, or use approximations for limiting quantities that result in biased training objectives. Riemannian Flow Matching bypasses these limitations and offers several advantages over previous approaches: it is simulation-free on simple geometries, does not require divergence computation, and computes its target vector field in close"},"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":"2302.03660","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T18:21:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"91b2db09b5aef8c8cad927fb6832c5a8a9cf9b6ca2160eedae39b2c95e4dd378","abstract_canon_sha256":"d2b8620036d307ef785e6bfbef67c4839fdee35615d4e765113db7f1733a3ac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:11.040212Z","signature_b64":"BQyoEr0T9jKWSlOIzPdSv0AZFrb5BnEg4Ju8+/7oADplOp3/AoYbAP5YaABs4HKpWFz0l9Yj8w/6Ia5NTMBuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7eb6382d85defa8c991c483f5d12049cc1a61426d53169f91895501355d628","last_reissued_at":"2026-07-05T07:49:11.039791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:11.039791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Matching on General Geometries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ricky T. Q. Chen, Yaron Lipman","submitted_at":"2023-02-07T18:21:24Z","abstract_excerpt":"We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training continuous normalizing flows on manifolds. Existing methods for generative modeling on manifolds either require expensive simulation, are inherently unable to scale to high dimensions, or use approximations for limiting quantities that result in biased training objectives. Riemannian Flow Matching bypasses these limitations and offers several advantages over previous approaches: it is simulation-free on simple geometries, does not require divergence computation, and computes its target vector field in close"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03660","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/2302.03660/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":"2302.03660","created_at":"2026-07-05T07:49:11.039849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03660v3","created_at":"2026-07-05T07:49:11.039849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03660","created_at":"2026-07-05T07:49:11.039849+00:00"},{"alias_kind":"pith_short_12","alias_value":"557LMOBNQXPP","created_at":"2026-07-05T07:49:11.039849+00:00"},{"alias_kind":"pith_short_16","alias_value":"557LMOBNQXPPVDEZ","created_at":"2026-07-05T07:49:11.039849+00:00"},{"alias_kind":"pith_short_8","alias_value":"557LMOBN","created_at":"2026-07-05T07:49:11.039849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06114","citing_title":"x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21256","citing_title":"Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00947","citing_title":"Diffeomorphic Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06278","citing_title":"Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31288","citing_title":"Probabilistic Inversion with Flow Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15193","citing_title":"Aligning Latent Geometry for Spherical Flow Matching in Image Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29105","citing_title":"Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26535","citing_title":"Recursive Flow Matching","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17354","citing_title":"CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13618","citing_title":"On the Importance of Tactile Sensing for Imitation Learning: A Case Study on Robotic Match Lighting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21981","citing_title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17354","citing_title":"CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07213","citing_title":"Diffusion Processes on Implicit Manifolds","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18472","citing_title":"Flowing with Confidence","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19305","citing_title":"Mat\\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16755","citing_title":"Learning Unbiased Permutations via Flow Matching","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22564","citing_title":"MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03360","citing_title":"A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02222","citing_title":"Generative Modeling with Orbit-Space Particle Flow Matching","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06591","citing_title":"BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21809","citing_title":"Quotient-Space Diffusion Models","ref_index":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS","json":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS.json","graph_json":"https://pith.science/api/pith-number/557LMOBNQXPPVDEZDRED6XISAS/graph.json","events_json":"https://pith.science/api/pith-number/557LMOBNQXPPVDEZDRED6XISAS/events.json","paper":"https://pith.science/paper/557LMOBN"},"agent_actions":{"view_html":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS","download_json":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS.json","view_paper":"https://pith.science/paper/557LMOBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03660&json=true","fetch_graph":"https://pith.science/api/pith-number/557LMOBNQXPPVDEZDRED6XISAS/graph.json","fetch_events":"https://pith.science/api/pith-number/557LMOBNQXPPVDEZDRED6XISAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS/action/storage_attestation","attest_author":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS/action/author_attestation","sign_citation":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS/action/citation_signature","submit_replication":"https://pith.science/pith/557LMOBNQXPPVDEZDRED6XISAS/action/replication_record"}},"created_at":"2026-07-05T07:49:11.039849+00:00","updated_at":"2026-07-05T07:49:11.039849+00:00"}