{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTK43J7U34WD5XJROZBDS36J7J","short_pith_number":"pith:NTK43J7U","schema_version":"1.0","canonical_sha256":"6cd5cda7f4df2c3edd317642396fc9fa5410636022f3b04e04c6f88f17476b0e","source":{"kind":"arxiv","id":"2412.00100","version":1},"attestation_state":"computed","paper":{"title":"Steering Rectified Flow Models in the Vector Field for Controlled Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Maitreya Patel, Song Wen, Yezhou Yang","submitted_at":"2024-11-27T19:04:40Z","abstract_excerpt":"Diffusion models (DMs) excel in photorealism, image editing, and solving inverse problems, aided by classifier-free guidance and image inversion techniques. However, rectified flow models (RFMs) remain underexplored for these tasks. Existing DM-based methods often require additional training, lack generalization to pretrained latent models, underperform, and demand significant computational resources due to extensive backpropagation through ODE solvers and inversion processes. In this work, we first develop a theoretical and empirical understanding of the vector field dynamics of RFMs in effic"},"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":"2412.00100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T19:04:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"dc8b6389d63da72b6c4b4f52dba402bd4f25418150e955026257c6b47441b7ed","abstract_canon_sha256":"51b86367054631974441716a6c7dea16f9f7abe6a4ee5feaed3c45d22c3e89af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:36.224486Z","signature_b64":"ByTPTkM5WhaPXUzqIlc0ZbSsCIWRZYDHgTgIBfWVik9Y1We6kGa+0rjzkiskjkz/OTo9gW8QMqcKRpWK2/Z9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd5cda7f4df2c3edd317642396fc9fa5410636022f3b04e04c6f88f17476b0e","last_reissued_at":"2026-07-05T09:42:36.223976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:36.223976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Steering Rectified Flow Models in the Vector Field for Controlled Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Maitreya Patel, Song Wen, Yezhou Yang","submitted_at":"2024-11-27T19:04:40Z","abstract_excerpt":"Diffusion models (DMs) excel in photorealism, image editing, and solving inverse problems, aided by classifier-free guidance and image inversion techniques. However, rectified flow models (RFMs) remain underexplored for these tasks. Existing DM-based methods often require additional training, lack generalization to pretrained latent models, underperform, and demand significant computational resources due to extensive backpropagation through ODE solvers and inversion processes. In this work, we first develop a theoretical and empirical understanding of the vector field dynamics of RFMs in effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00100","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.00100/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":"2412.00100","created_at":"2026-07-05T09:42:36.224043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00100v1","created_at":"2026-07-05T09:42:36.224043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00100","created_at":"2026-07-05T09:42:36.224043+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTK43J7U34WD","created_at":"2026-07-05T09:42:36.224043+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTK43J7U34WD5XJR","created_at":"2026-07-05T09:42:36.224043+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTK43J7U","created_at":"2026-07-05T09:42:36.224043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22958","citing_title":"PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28785","citing_title":"Stochastic Optimal Control Sampling for Diffusion Inverse Problems","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26391","citing_title":"Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16520","citing_title":"Saving Foundation Flow-Matching Priors for Inverse Problems","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07150","citing_title":"FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18365","citing_title":"Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19974","citing_title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J","json":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J.json","graph_json":"https://pith.science/api/pith-number/NTK43J7U34WD5XJROZBDS36J7J/graph.json","events_json":"https://pith.science/api/pith-number/NTK43J7U34WD5XJROZBDS36J7J/events.json","paper":"https://pith.science/paper/NTK43J7U"},"agent_actions":{"view_html":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J","download_json":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J.json","view_paper":"https://pith.science/paper/NTK43J7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00100&json=true","fetch_graph":"https://pith.science/api/pith-number/NTK43J7U34WD5XJROZBDS36J7J/graph.json","fetch_events":"https://pith.science/api/pith-number/NTK43J7U34WD5XJROZBDS36J7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J/action/storage_attestation","attest_author":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J/action/author_attestation","sign_citation":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J/action/citation_signature","submit_replication":"https://pith.science/pith/NTK43J7U34WD5XJROZBDS36J7J/action/replication_record"}},"created_at":"2026-07-05T09:42:36.224043+00:00","updated_at":"2026-07-05T09:42:36.224043+00:00"}