{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4EPMU4O2CSLLXOQZWJANFA3XBE","short_pith_number":"pith:4EPMU4O2","schema_version":"1.0","canonical_sha256":"e11eca71da1496bbba19b240d2837709253c48abad56cf4e459cc4af7892574a","source":{"kind":"arxiv","id":"2312.04965","version":1},"attestation_state":"computed","paper":{"title":"Inversion-Free Image Editing with Natural Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiayi Pan, Joyce Chai, Sihan Xu, Yidong Huang, Ziqiao Ma","submitted_at":"2023-12-07T18:58:27Z","abstract_excerpt":"Despite recent advances in inversion-based editing, text-guided image manipulation remains challenging for diffusion models. The primary bottlenecks include 1) the time-consuming nature of the inversion process; 2) the struggle to balance consistency with accuracy; 3) the lack of compatibility with efficient consistency sampling methods used in consistency models. To address the above issues, we start by asking ourselves if the inversion process can be eliminated for editing. We show that when the initial sample is known, a special variance schedule reduces the denoising step to the same form "},"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":"2312.04965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T18:58:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"15625a740d4c1248e5b7634f3a78896d005bc8821da5f021bdb357b0377db226","abstract_canon_sha256":"5a89dc8bbcb5c4a04b5a69baf38907ccad75ff85b80975b6ba035df3e5bf3ff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:55.092090Z","signature_b64":"I/lmqNCcut267EiL1fWvImgAoMc+9PkjEO+qk0g7mvawM7GJ6v/7750aJFz1KcJpU0SFd8bkGHlzEegLEK9fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11eca71da1496bbba19b240d2837709253c48abad56cf4e459cc4af7892574a","last_reissued_at":"2026-07-05T07:21:55.091662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:55.091662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inversion-Free Image Editing with Natural Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiayi Pan, Joyce Chai, Sihan Xu, Yidong Huang, Ziqiao Ma","submitted_at":"2023-12-07T18:58:27Z","abstract_excerpt":"Despite recent advances in inversion-based editing, text-guided image manipulation remains challenging for diffusion models. The primary bottlenecks include 1) the time-consuming nature of the inversion process; 2) the struggle to balance consistency with accuracy; 3) the lack of compatibility with efficient consistency sampling methods used in consistency models. To address the above issues, we start by asking ourselves if the inversion process can be eliminated for editing. We show that when the initial sample is known, a special variance schedule reduces the denoising step to the same form "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04965","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/2312.04965/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":"2312.04965","created_at":"2026-07-05T07:21:55.091715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04965v1","created_at":"2026-07-05T07:21:55.091715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04965","created_at":"2026-07-05T07:21:55.091715+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EPMU4O2CSLL","created_at":"2026-07-05T07:21:55.091715+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EPMU4O2CSLLXOQZ","created_at":"2026-07-05T07:21:55.091715+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EPMU4O2","created_at":"2026-07-05T07:21:55.091715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26535","citing_title":"Recursive Flow Matching","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15661","citing_title":"VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08536","citing_title":"RewardFlow: Generate Images by Optimizing What You Reward","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE","json":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE.json","graph_json":"https://pith.science/api/pith-number/4EPMU4O2CSLLXOQZWJANFA3XBE/graph.json","events_json":"https://pith.science/api/pith-number/4EPMU4O2CSLLXOQZWJANFA3XBE/events.json","paper":"https://pith.science/paper/4EPMU4O2"},"agent_actions":{"view_html":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE","download_json":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE.json","view_paper":"https://pith.science/paper/4EPMU4O2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04965&json=true","fetch_graph":"https://pith.science/api/pith-number/4EPMU4O2CSLLXOQZWJANFA3XBE/graph.json","fetch_events":"https://pith.science/api/pith-number/4EPMU4O2CSLLXOQZWJANFA3XBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE/action/storage_attestation","attest_author":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE/action/author_attestation","sign_citation":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE/action/citation_signature","submit_replication":"https://pith.science/pith/4EPMU4O2CSLLXOQZWJANFA3XBE/action/replication_record"}},"created_at":"2026-07-05T07:21:55.091715+00:00","updated_at":"2026-07-05T07:21:55.091715+00:00"}