{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RIIXQLID6LH6IJ64PGRIN4UWFC","short_pith_number":"pith:RIIXQLID","schema_version":"1.0","canonical_sha256":"8a11782d03f2cfe427dc79a286f296288ec0d3a6380ae632e459079027bea2e9","source":{"kind":"arxiv","id":"2209.14577","version":1},"attestation_state":"computed","paper":{"title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qiang Liu","submitted_at":"2022-09-29T06:37:26Z","abstract_excerpt":"We present a flow-based approach to the optimal transport (OT) problem between two continuous distributions $\\pi_0,\\pi_1$ on $\\mathbb{R}^d$, of minimizing a transport cost $\\mathbb{E}[c(X_1-X_0)]$ in the set of couplings $(X_0,X_1)$ whose marginal distributions on $X_0,X_1$ equals $\\pi_0,\\pi_1$, respectively, where $c$ is a cost function. Our method iteratively constructs a sequence of neural ordinary differentiable equations (ODE), each learned by solving a simple unconstrained regression problem, which monotonically reduce the transport cost while automatically preserving the marginal constr"},"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":"2209.14577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T06:37:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a34fced3b0bdfcc0dde879d3d41bbe965001b013e8dc9ee04b26e693beea3ce0","abstract_canon_sha256":"f567ee22775b2fd7ed6e6fc907783e0b8e1535420db9f0c6947b2d0edd0a1e1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:59:04.406636Z","signature_b64":"JU0+KBUyTANBuaDByMdAmkc38t2lt54S2GTCvvdl5doyPDYV17mRWWF9z6pN1+HmzUGA2jJ3wqPo8W6d+TxGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a11782d03f2cfe427dc79a286f296288ec0d3a6380ae632e459079027bea2e9","last_reissued_at":"2026-05-18T02:59:04.406016Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:59:04.406016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qiang Liu","submitted_at":"2022-09-29T06:37:26Z","abstract_excerpt":"We present a flow-based approach to the optimal transport (OT) problem between two continuous distributions $\\pi_0,\\pi_1$ on $\\mathbb{R}^d$, of minimizing a transport cost $\\mathbb{E}[c(X_1-X_0)]$ in the set of couplings $(X_0,X_1)$ whose marginal distributions on $X_0,X_1$ equals $\\pi_0,\\pi_1$, respectively, where $c$ is a cost function. Our method iteratively constructs a sequence of neural ordinary differentiable equations (ODE), each learned by solving a simple unconstrained regression problem, which monotonically reduce the transport cost while automatically preserving the marginal constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14577","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":""},"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":"2209.14577","created_at":"2026-05-18T02:59:04.406109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14577v1","created_at":"2026-05-18T02:59:04.406109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14577","created_at":"2026-05-18T02:59:04.406109+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIIXQLID6LH6","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIIXQLID6LH6IJ64","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIIXQLID","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21831","citing_title":"Generative Modeling of Discrete Data Using Geometric Latent Subspaces","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2602.07322","citing_title":"Action-to-Action Flow Matching","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.08155","citing_title":"C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12805","citing_title":"Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12964","citing_title":"Asymmetric Flow Models","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12379","citing_title":"Discrete Flow Matching for Offline-to-Online Reinforcement Learning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2209.15571","citing_title":"Building Normalizing Flows with Stochastic Interpolants","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2209.15571","citing_title":"Building Normalizing Flows with Stochastic Interpolants","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01844","citing_title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22379","citing_title":"Efficient Diffusion Distillation via Embedding Loss","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04342","citing_title":"Generative models for decision-making under distributional shift","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2410.24164","citing_title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17706","citing_title":"OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC","json":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC.json","graph_json":"https://pith.science/api/pith-number/RIIXQLID6LH6IJ64PGRIN4UWFC/graph.json","events_json":"https://pith.science/api/pith-number/RIIXQLID6LH6IJ64PGRIN4UWFC/events.json","paper":"https://pith.science/paper/RIIXQLID"},"agent_actions":{"view_html":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC","download_json":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC.json","view_paper":"https://pith.science/paper/RIIXQLID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14577&json=true","fetch_graph":"https://pith.science/api/pith-number/RIIXQLID6LH6IJ64PGRIN4UWFC/graph.json","fetch_events":"https://pith.science/api/pith-number/RIIXQLID6LH6IJ64PGRIN4UWFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC/action/storage_attestation","attest_author":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC/action/author_attestation","sign_citation":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC/action/citation_signature","submit_replication":"https://pith.science/pith/RIIXQLID6LH6IJ64PGRIN4UWFC/action/replication_record"}},"created_at":"2026-05-18T02:59:04.406109+00:00","updated_at":"2026-05-18T02:59:04.406109+00:00"}