{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KUFIQF7OWO4UQV5WPBFVX2QJMJ","short_pith_number":"pith:KUFIQF7O","schema_version":"1.0","canonical_sha256":"550a8817eeb3b94857b6784b5bea09624539784bad07595958467096067e5bef","source":{"kind":"arxiv","id":"2310.01506","version":2},"attestation_state":"computed","paper":{"title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Qiang Xu, Shaoteng Liu, Xuan Ju, Yuxuan Bian","submitted_at":"2023-10-02T18:01:55Z","abstract_excerpt":"Text-guided diffusion models have revolutionized image generation and editing, offering exceptional realism and diversity. Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt, the process commences by acquiring a noisy latent vector corresponding to the source image via the diffusion model. This vector is subsequently fed into separate source and target diffusion branches for editing. The accuracy of this inversion process significantly impacts the final editing outcome, influencing both essential content preservation of the sour"},"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":"2310.01506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T18:01:55Z","cross_cats_sorted":[],"title_canon_sha256":"f39d059daa5518af5779619b6fc86848a8f2af47b32de3fcbe45c37ba8971772","abstract_canon_sha256":"e55194c29793c21c392126c3bbf80d96ce57da82cd5c0e86b96d946dd73aa43b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:32.809684Z","signature_b64":"xkMAajB5TD2vcf1qQEoo+XXTaV/kulTmCqk3XXtxQ46nf2Jll2D9xDn7hbrJlCM8B+ZpcVd2sahen6Hy1b1zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"550a8817eeb3b94857b6784b5bea09624539784bad07595958467096067e5bef","last_reissued_at":"2026-07-05T07:02:32.809153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:32.809153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Qiang Xu, Shaoteng Liu, Xuan Ju, Yuxuan Bian","submitted_at":"2023-10-02T18:01:55Z","abstract_excerpt":"Text-guided diffusion models have revolutionized image generation and editing, offering exceptional realism and diversity. Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt, the process commences by acquiring a noisy latent vector corresponding to the source image via the diffusion model. This vector is subsequently fed into separate source and target diffusion branches for editing. The accuracy of this inversion process significantly impacts the final editing outcome, influencing both essential content preservation of the sour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01506","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/2310.01506/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":"2310.01506","created_at":"2026-07-05T07:02:32.809239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01506v2","created_at":"2026-07-05T07:02:32.809239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01506","created_at":"2026-07-05T07:02:32.809239+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUFIQF7OWO4U","created_at":"2026-07-05T07:02:32.809239+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUFIQF7OWO4UQV5W","created_at":"2026-07-05T07:02:32.809239+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUFIQF7O","created_at":"2026-07-05T07:02:32.809239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07051","citing_title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09901","citing_title":"On the Controllability-Fidelity Frontier in Diffusion Editing","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07145","citing_title":"Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04457","citing_title":"Imagine Before You Draw: Visual Prompt Engineering for Image Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01380","citing_title":"Training-free image inversion for one-step diffusion models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22244","citing_title":"FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16399","citing_title":"Stable and Near-Reversible Diffusion ODE Solvers for Image Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15661","citing_title":"VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18438","citing_title":"CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20360","citing_title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07951","citing_title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21045","citing_title":"LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25128","citing_title":"ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08536","citing_title":"RewardFlow: Generate Images by Optimizing What You Reward","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14591","citing_title":"Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20258","citing_title":"Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02417","citing_title":"DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ","json":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ.json","graph_json":"https://pith.science/api/pith-number/KUFIQF7OWO4UQV5WPBFVX2QJMJ/graph.json","events_json":"https://pith.science/api/pith-number/KUFIQF7OWO4UQV5WPBFVX2QJMJ/events.json","paper":"https://pith.science/paper/KUFIQF7O"},"agent_actions":{"view_html":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ","download_json":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ.json","view_paper":"https://pith.science/paper/KUFIQF7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01506&json=true","fetch_graph":"https://pith.science/api/pith-number/KUFIQF7OWO4UQV5WPBFVX2QJMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KUFIQF7OWO4UQV5WPBFVX2QJMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ/action/storage_attestation","attest_author":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ/action/author_attestation","sign_citation":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ/action/citation_signature","submit_replication":"https://pith.science/pith/KUFIQF7OWO4UQV5WPBFVX2QJMJ/action/replication_record"}},"created_at":"2026-07-05T07:02:32.809239+00:00","updated_at":"2026-07-05T07:02:32.809239+00:00"}