{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAXCM4FPXORUFRVHQRSLN5EJCM","short_pith_number":"pith:DAXCM4FP","schema_version":"1.0","canonical_sha256":"182e2670afbba342c6a78464b6f48913028bfa4732a184ab52c41bfe77df7e42","source":{"kind":"arxiv","id":"2510.08532","version":2},"attestation_state":"computed","paper":{"title":"Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Daniil Ostashev, Kuan-Chieh Wang, Or Patashnik, Rishubh Parihar, R. Venkatesh Babu","submitted_at":"2025-10-09T17:51:03Z","abstract_excerpt":"Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained control over the extent of edits. We introduce Kontinuous Kontext, an instruction-driven editing model that provides a new dimension of control over edit strength, enabling users to adjust edits gradually from no change to a fully realized result in a smooth and continuous manner. Kontinuous Kontext extends a state-of-the-art image editing model to accept an additional input, a scalar edit strength which is then paired w"},"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":"2510.08532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-09T17:51:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d152e33e863a168eed79246c045b1a09b45207da1fe724389101cf6c3b1b414b","abstract_canon_sha256":"f87dc8350d59da5a6e855f4872d8561ab56f884a29130a999c9d42a36a17b3f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:22:14.462465Z","signature_b64":"hgk2CiJb/27nQC/0Z4htPkkqHYHEuBOEyJfRnWW/OrJW393bSf0g8KczuPBw4DHXLrCV4hTS++2R5W0XPNneDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"182e2670afbba342c6a78464b6f48913028bfa4732a184ab52c41bfe77df7e42","last_reissued_at":"2026-07-22T01:22:14.461621Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:22:14.461621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Daniil Ostashev, Kuan-Chieh Wang, Or Patashnik, Rishubh Parihar, R. Venkatesh Babu","submitted_at":"2025-10-09T17:51:03Z","abstract_excerpt":"Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained control over the extent of edits. We introduce Kontinuous Kontext, an instruction-driven editing model that provides a new dimension of control over edit strength, enabling users to adjust edits gradually from no change to a fully realized result in a smooth and continuous manner. Kontinuous Kontext extends a state-of-the-art image editing model to accept an additional input, a scalar edit strength which is then paired w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08532","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/2510.08532/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":"2510.08532","created_at":"2026-07-22T01:22:14.462024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08532v2","created_at":"2026-07-22T01:22:14.462024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08532","created_at":"2026-07-22T01:22:14.462024+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAXCM4FPXORU","created_at":"2026-07-22T01:22:14.462024+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAXCM4FPXORUFRVH","created_at":"2026-07-22T01:22:14.462024+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAXCM4FP","created_at":"2026-07-22T01:22:14.462024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2606.24021","citing_title":"Token-to-Token Alignment of Text Embeddings for Semantic Blending","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":115,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20556","citing_title":"Thinking in Boxes: 3D Editing in Real Images Made Easy","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12494","citing_title":"Net-Ev$^2$: A Generative Simulator for Network Event Evolution","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25569","citing_title":"ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20816","citing_title":"ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM","json":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM.json","graph_json":"https://pith.science/api/pith-number/DAXCM4FPXORUFRVHQRSLN5EJCM/graph.json","events_json":"https://pith.science/api/pith-number/DAXCM4FPXORUFRVHQRSLN5EJCM/events.json","paper":"https://pith.science/paper/DAXCM4FP"},"agent_actions":{"view_html":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM","download_json":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM.json","view_paper":"https://pith.science/paper/DAXCM4FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08532&json=true","fetch_graph":"https://pith.science/api/pith-number/DAXCM4FPXORUFRVHQRSLN5EJCM/graph.json","fetch_events":"https://pith.science/api/pith-number/DAXCM4FPXORUFRVHQRSLN5EJCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM/action/storage_attestation","attest_author":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM/action/author_attestation","sign_citation":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM/action/citation_signature","submit_replication":"https://pith.science/pith/DAXCM4FPXORUFRVHQRSLN5EJCM/action/replication_record"}},"created_at":"2026-07-22T01:22:14.462024+00:00","updated_at":"2026-07-22T01:22:14.462024+00:00"}