{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DIFNKROGE5IVIU3AIXYJKM2ETX","short_pith_number":"pith:DIFNKROG","schema_version":"1.0","canonical_sha256":"1a0ad545c6275154536045f09533449dca0fb88c808fa6e1607dd7918259c204","source":{"kind":"arxiv","id":"2406.00457","version":1},"attestation_state":"computed","paper":{"title":"The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag, Yusuf Dalva","submitted_at":"2024-06-01T14:46:57Z","abstract_excerpt":"Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level of precise attribute manipulation without compromising image coherence. In this paper, CLIP which is often used in popular text-to-image diffusion models such as Stable Diffusion is capable of performing disentangled editing in a zero-shot manner. Through both qualitative and quantitative comparisons with state-of-the-art editing methods, we show that our a"},"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":"2406.00457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T14:46:57Z","cross_cats_sorted":[],"title_canon_sha256":"cf69f809eb56a5ed6a556b626b173ed4794f6ddb237f80d789de03324bf7f572","abstract_canon_sha256":"838f0b30ae3f91561dab67a36c76ec7ebf8f460965bd442ec0c393c41c8a9e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:02.227028Z","signature_b64":"WC+kJ+u4sBc0WN0lKFFZB31DwDzU/TvCAtEjyX9c6ss92KCGrpAFYIqusYzKUcOT/KAsm5ZN18fK4AS/4t8zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a0ad545c6275154536045f09533449dca0fb88c808fa6e1607dd7918259c204","last_reissued_at":"2026-07-05T08:26:02.226558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:02.226558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag, Yusuf Dalva","submitted_at":"2024-06-01T14:46:57Z","abstract_excerpt":"Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level of precise attribute manipulation without compromising image coherence. In this paper, CLIP which is often used in popular text-to-image diffusion models such as Stable Diffusion is capable of performing disentangled editing in a zero-shot manner. Through both qualitative and quantitative comparisons with state-of-the-art editing methods, we show that our a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00457","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/2406.00457/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":"2406.00457","created_at":"2026-07-05T08:26:02.226619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00457v1","created_at":"2026-07-05T08:26:02.226619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00457","created_at":"2026-07-05T08:26:02.226619+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIFNKROGE5IV","created_at":"2026-07-05T08:26:02.226619+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIFNKROGE5IVIU3A","created_at":"2026-07-05T08:26:02.226619+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIFNKROG","created_at":"2026-07-05T08:26:02.226619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23758","citing_title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX","json":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX.json","graph_json":"https://pith.science/api/pith-number/DIFNKROGE5IVIU3AIXYJKM2ETX/graph.json","events_json":"https://pith.science/api/pith-number/DIFNKROGE5IVIU3AIXYJKM2ETX/events.json","paper":"https://pith.science/paper/DIFNKROG"},"agent_actions":{"view_html":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX","download_json":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX.json","view_paper":"https://pith.science/paper/DIFNKROG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00457&json=true","fetch_graph":"https://pith.science/api/pith-number/DIFNKROGE5IVIU3AIXYJKM2ETX/graph.json","fetch_events":"https://pith.science/api/pith-number/DIFNKROGE5IVIU3AIXYJKM2ETX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX/action/storage_attestation","attest_author":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX/action/author_attestation","sign_citation":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX/action/citation_signature","submit_replication":"https://pith.science/pith/DIFNKROGE5IVIU3AIXYJKM2ETX/action/replication_record"}},"created_at":"2026-07-05T08:26:02.226619+00:00","updated_at":"2026-07-05T08:26:02.226619+00:00"}