{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVVUPZ62F5CHAJPOXKOLESFOFB","short_pith_number":"pith:MVVUPZ62","schema_version":"1.0","canonical_sha256":"656b47e7da2f447025eeba9cb248ae286177439150bc4605932f1ef567ed1cdb","source":{"kind":"arxiv","id":"2410.10792","version":1},"attestation_state":"computed","paper":{"title":"Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Litu Rout, Nataniel Ruiz, Sanjay Shakkottai, Wen-Sheng Chu, Yujia Chen","submitted_at":"2024-10-14T17:56:24Z","abstract_excerpt":"Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using stochastic equivalents of rectified flow models (such as Flux). Although Diffusion Models (DMs) have recently dominated the field of generative modeling for images, their inversion presents faithfulness and editability challenges due to nonlinearities in drift and diffusion. Existing state-of-the-art DM inversion approaches rely on training of additional paramete"},"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":"2410.10792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T17:56:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ad491e6ae988da765b5f500b73a38e36c8bc8a5f232255b128d1c5ffc466c710","abstract_canon_sha256":"cbeeedf926b29bf219b8d8664803e2652bcf03e65d38b22f3e7dea8ea8de5da8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:20.920051Z","signature_b64":"FJ/MCuzN4y2DJjeI+/LMFU2jXC9KfNTNKBxjoMWWgF5KR7LMmXvKAkO6JcTLFNzmqX/i9oHJfBJfTm91O8BXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656b47e7da2f447025eeba9cb248ae286177439150bc4605932f1ef567ed1cdb","last_reissued_at":"2026-07-05T09:20:20.919577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:20.919577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Litu Rout, Nataniel Ruiz, Sanjay Shakkottai, Wen-Sheng Chu, Yujia Chen","submitted_at":"2024-10-14T17:56:24Z","abstract_excerpt":"Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using stochastic equivalents of rectified flow models (such as Flux). Although Diffusion Models (DMs) have recently dominated the field of generative modeling for images, their inversion presents faithfulness and editability challenges due to nonlinearities in drift and diffusion. Existing state-of-the-art DM inversion approaches rely on training of additional paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10792","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/2410.10792/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":"2410.10792","created_at":"2026-07-05T09:20:20.919640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10792v1","created_at":"2026-07-05T09:20:20.919640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10792","created_at":"2026-07-05T09:20:20.919640+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVVUPZ62F5CH","created_at":"2026-07-05T09:20:20.919640+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVVUPZ62F5CHAJPO","created_at":"2026-07-05T09:20:20.919640+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVVUPZ62","created_at":"2026-07-05T09:20:20.919640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22304","citing_title":"Encoder-Decoder Manifold Alignment for Idempotent Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19629","citing_title":"RIVET: Robust Idempotent Voice Attribute Editing","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17584","citing_title":"Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09901","citing_title":"On the Controllability-Fidelity Frontier in Diffusion Editing","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07760","citing_title":"scCBGM: Interpretable Single-Cell Counterfactual Editing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07145","citing_title":"Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":61,"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":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15661","citing_title":"VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14543","citing_title":"Exploring Cross-Modal Flows for Few-Shot Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18365","citing_title":"Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19974","citing_title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14708","citing_title":"StyleTextGen: Style-Conditioned Multilingual Scene Text Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13047","citing_title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20038","citing_title":"FluSplat: Sparse-View 3D Editing without Test-Time Optimization","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14914","citing_title":"Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15871","citing_title":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21362","citing_title":"KD-CVG: A Knowledge-Driven Approach for Creative Video Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02417","citing_title":"DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB","json":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB.json","graph_json":"https://pith.science/api/pith-number/MVVUPZ62F5CHAJPOXKOLESFOFB/graph.json","events_json":"https://pith.science/api/pith-number/MVVUPZ62F5CHAJPOXKOLESFOFB/events.json","paper":"https://pith.science/paper/MVVUPZ62"},"agent_actions":{"view_html":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB","download_json":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB.json","view_paper":"https://pith.science/paper/MVVUPZ62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10792&json=true","fetch_graph":"https://pith.science/api/pith-number/MVVUPZ62F5CHAJPOXKOLESFOFB/graph.json","fetch_events":"https://pith.science/api/pith-number/MVVUPZ62F5CHAJPOXKOLESFOFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB/action/storage_attestation","attest_author":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB/action/author_attestation","sign_citation":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB/action/citation_signature","submit_replication":"https://pith.science/pith/MVVUPZ62F5CHAJPOXKOLESFOFB/action/replication_record"}},"created_at":"2026-07-05T09:20:20.919640+00:00","updated_at":"2026-07-05T09:20:20.919640+00:00"}