{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YTEYJ2FJ3EEU5ACSSZ5K5MBOJX","short_pith_number":"pith:YTEYJ2FJ","schema_version":"1.0","canonical_sha256":"c4c984e8a9d9094e8052967aaeb02e4dd35e488f9e3f209fb3763b633bc29a14","source":{"kind":"arxiv","id":"2204.02491","version":2},"attestation_state":"computed","paper":{"title":"Text2LIVE: Text-Driven Layered Image and Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dolev Ofri-Amar, Omer Bar-Tal, Rafail Fridman, Tali Dekel, Yoni Kasten","submitted_at":"2022-04-05T21:17:34Z","abstract_excerpt":"We present a method for zero-shot, text-driven appearance manipulation in natural images and videos. Given an input image or video and a target text prompt, our goal is to edit the appearance of existing objects (e.g., object's texture) or augment the scene with visual effects (e.g., smoke, fire) in a semantically meaningful manner. We train a generator using an internal dataset of training examples, extracted from a single input (image or video and target text prompt), while leveraging an external pre-trained CLIP model to establish our losses. Rather than directly generating the edited outpu"},"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":"2204.02491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T21:17:34Z","cross_cats_sorted":[],"title_canon_sha256":"22cd7bbc029e8948f525af75dfa14d7948de6e2216e93b6954bbb3e6edd26a42","abstract_canon_sha256":"3902f10c251a9d044feaa4b9ec627d07d8ba45f8e655eccb359e0cdc9094bafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:23.191699Z","signature_b64":"kPqqtELgZIjDYsEJj7goX+dCZth36sVna+Awtr1RL3QJ9nViWtbH+oFSqYcv1+YaD0juFyhovkMdNIVmQ7qhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4c984e8a9d9094e8052967aaeb02e4dd35e488f9e3f209fb3763b633bc29a14","last_reissued_at":"2026-07-05T04:26:23.191162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:23.191162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2LIVE: Text-Driven Layered Image and Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dolev Ofri-Amar, Omer Bar-Tal, Rafail Fridman, Tali Dekel, Yoni Kasten","submitted_at":"2022-04-05T21:17:34Z","abstract_excerpt":"We present a method for zero-shot, text-driven appearance manipulation in natural images and videos. Given an input image or video and a target text prompt, our goal is to edit the appearance of existing objects (e.g., object's texture) or augment the scene with visual effects (e.g., smoke, fire) in a semantically meaningful manner. We train a generator using an internal dataset of training examples, extracted from a single input (image or video and target text prompt), while leveraging an external pre-trained CLIP model to establish our losses. Rather than directly generating the edited outpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02491","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/2204.02491/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":"2204.02491","created_at":"2026-07-05T04:26:23.191226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02491v2","created_at":"2026-07-05T04:26:23.191226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02491","created_at":"2026-07-05T04:26:23.191226+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTEYJ2FJ3EEU","created_at":"2026-07-05T04:26:23.191226+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTEYJ2FJ3EEU5ACS","created_at":"2026-07-05T04:26:23.191226+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTEYJ2FJ","created_at":"2026-07-05T04:26:23.191226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2208.01626","citing_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX","json":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX.json","graph_json":"https://pith.science/api/pith-number/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/graph.json","events_json":"https://pith.science/api/pith-number/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/events.json","paper":"https://pith.science/paper/YTEYJ2FJ"},"agent_actions":{"view_html":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX","download_json":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX.json","view_paper":"https://pith.science/paper/YTEYJ2FJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02491&json=true","fetch_graph":"https://pith.science/api/pith-number/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/graph.json","fetch_events":"https://pith.science/api/pith-number/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/action/storage_attestation","attest_author":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/action/author_attestation","sign_citation":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/action/citation_signature","submit_replication":"https://pith.science/pith/YTEYJ2FJ3EEU5ACSSZ5K5MBOJX/action/replication_record"}},"created_at":"2026-07-05T04:26:23.191226+00:00","updated_at":"2026-07-05T04:26:23.191226+00:00"}