{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KIO5KBY4RSPYPWEINCEEG2YUA5","short_pith_number":"pith:KIO5KBY4","schema_version":"1.0","canonical_sha256":"521dd5071c8c9f87d8886888436b1407566009c1949994ede3fcc32a6672e1a7","source":{"kind":"arxiv","id":"2312.09256","version":2},"attestation_state":"computed","paper":{"title":"LIME: Localized Image Editing via Attention Regularization in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Enis Simsar, Federico Tombari, Thomas Hofmann, Yongqin Xian","submitted_at":"2023-12-14T18:59:59Z","abstract_excerpt":"Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A significant challenge within this domain is localized editing, where specific areas of an image are modified without affecting the rest of the content. This paper introduces LIME for localized image editing in diffusion models. LIME does not require user-specified regions of interest (RoI) or additional text input, but rather employs features from pre-trained metho"},"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":"2312.09256","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"24b94640a7c9a080c5225ae8206f7a23b6913e00697c9722b4f85e315a330346","abstract_canon_sha256":"5ec1ad8192a555e8cb95b66ce5a3868eed6956ebbf4a390ea2bf95dd53a95020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:49.145515Z","signature_b64":"QC6cChyl0P/PiltFNhakOWp3URYce/O3WLugsWoUW5Es+O896U8FTgRRvdGiy9E9+yCJkx6EQAu2iqsGamaDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"521dd5071c8c9f87d8886888436b1407566009c1949994ede3fcc32a6672e1a7","last_reissued_at":"2026-07-05T09:44:49.144008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:49.144008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIME: Localized Image Editing via Attention Regularization in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Enis Simsar, Federico Tombari, Thomas Hofmann, Yongqin Xian","submitted_at":"2023-12-14T18:59:59Z","abstract_excerpt":"Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A significant challenge within this domain is localized editing, where specific areas of an image are modified without affecting the rest of the content. This paper introduces LIME for localized image editing in diffusion models. LIME does not require user-specified regions of interest (RoI) or additional text input, but rather employs features from pre-trained metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09256","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/2312.09256/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":"2312.09256","created_at":"2026-07-05T09:44:49.144070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09256v2","created_at":"2026-07-05T09:44:49.144070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09256","created_at":"2026-07-05T09:44:49.144070+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIO5KBY4RSPY","created_at":"2026-07-05T09:44:49.144070+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIO5KBY4RSPYPWEI","created_at":"2026-07-05T09:44:49.144070+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIO5KBY4","created_at":"2026-07-05T09:44:49.144070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13565","citing_title":"CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5","json":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5.json","graph_json":"https://pith.science/api/pith-number/KIO5KBY4RSPYPWEINCEEG2YUA5/graph.json","events_json":"https://pith.science/api/pith-number/KIO5KBY4RSPYPWEINCEEG2YUA5/events.json","paper":"https://pith.science/paper/KIO5KBY4"},"agent_actions":{"view_html":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5","download_json":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5.json","view_paper":"https://pith.science/paper/KIO5KBY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09256&json=true","fetch_graph":"https://pith.science/api/pith-number/KIO5KBY4RSPYPWEINCEEG2YUA5/graph.json","fetch_events":"https://pith.science/api/pith-number/KIO5KBY4RSPYPWEINCEEG2YUA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5/action/storage_attestation","attest_author":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5/action/author_attestation","sign_citation":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5/action/citation_signature","submit_replication":"https://pith.science/pith/KIO5KBY4RSPYPWEINCEEG2YUA5/action/replication_record"}},"created_at":"2026-07-05T09:44:49.144070+00:00","updated_at":"2026-07-05T09:44:49.144070+00:00"}