{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PMJOY2SBYG3AV6TOOBFOBPKE55","short_pith_number":"pith:PMJOY2SB","schema_version":"1.0","canonical_sha256":"7b12ec6a41c1b60afa6e704ae0bd44ef4e097a07ddb9b2990350f47a7de44401","source":{"kind":"arxiv","id":"2410.07303","version":2},"attestation_state":"computed","paper":{"title":"Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu-Yun Wang, Hongsheng Li, Ling Yang, Mengdi Wang, Zhaoyang Huang","submitted_at":"2024-10-09T17:43:38Z","abstract_excerpt":"Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. Its key components include: 1) using the diffusion form of flow-matching, 2) employing $\\boldsymbol v$-prediction, and 3) performing rectification (a.k.a. reflow). In this paper, we argue that the success of rectification primarily lies in using a pretrained diffusion model to obtain matched pairs of noise and samples, follo"},"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":"2410.07303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:43:38Z","cross_cats_sorted":[],"title_canon_sha256":"0a66ceeb5dfdf28a160ceb9a3200bb6c698aa18c4a2bb546dcea327629c72ee8","abstract_canon_sha256":"824eea5bc6869f7414d19aba8ffa23ab354f6825e551230dcbbdadfe1a84236d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:13.280609Z","signature_b64":"Qo3HglpwfngC6OVS6ad5CfQTqvYkh+MoCefX0L5IITo8SToRrdesu3Gey+QVuUoUfqnnGNUbFutUziY6BBIyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b12ec6a41c1b60afa6e704ae0bd44ef4e097a07ddb9b2990350f47a7de44401","last_reissued_at":"2026-07-05T09:19:13.280136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:13.280136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu-Yun Wang, Hongsheng Li, Ling Yang, Mengdi Wang, Zhaoyang Huang","submitted_at":"2024-10-09T17:43:38Z","abstract_excerpt":"Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. Its key components include: 1) using the diffusion form of flow-matching, 2) employing $\\boldsymbol v$-prediction, and 3) performing rectification (a.k.a. reflow). In this paper, we argue that the success of rectification primarily lies in using a pretrained diffusion model to obtain matched pairs of noise and samples, follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07303","kind":"arxiv","version":2},"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/2410.07303/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":"2410.07303","created_at":"2026-07-05T09:19:13.280192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07303v2","created_at":"2026-07-05T09:19:13.280192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07303","created_at":"2026-07-05T09:19:13.280192+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMJOY2SBYG3A","created_at":"2026-07-05T09:19:13.280192+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMJOY2SBYG3AV6TO","created_at":"2026-07-05T09:19:13.280192+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMJOY2SB","created_at":"2026-07-05T09:19:13.280192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08155","citing_title":"C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17244","citing_title":"Drift Flow Matching","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08155","citing_title":"C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15809","citing_title":"MMaDA: Multimodal Large Diffusion Language Models","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55","json":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55.json","graph_json":"https://pith.science/api/pith-number/PMJOY2SBYG3AV6TOOBFOBPKE55/graph.json","events_json":"https://pith.science/api/pith-number/PMJOY2SBYG3AV6TOOBFOBPKE55/events.json","paper":"https://pith.science/paper/PMJOY2SB"},"agent_actions":{"view_html":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55","download_json":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55.json","view_paper":"https://pith.science/paper/PMJOY2SB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07303&json=true","fetch_graph":"https://pith.science/api/pith-number/PMJOY2SBYG3AV6TOOBFOBPKE55/graph.json","fetch_events":"https://pith.science/api/pith-number/PMJOY2SBYG3AV6TOOBFOBPKE55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55/action/storage_attestation","attest_author":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55/action/author_attestation","sign_citation":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55/action/citation_signature","submit_replication":"https://pith.science/pith/PMJOY2SBYG3AV6TOOBFOBPKE55/action/replication_record"}},"created_at":"2026-07-05T09:19:13.280192+00:00","updated_at":"2026-07-05T09:19:13.280192+00:00"}