{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6Y5GUJZIPGNBLIQF5BVKRHS7UZ","short_pith_number":"pith:6Y5GUJZI","schema_version":"1.0","canonical_sha256":"f63a6a2728799a15a205e86aa89e5fa66147be991506af3908336620c0f454b0","source":{"kind":"arxiv","id":"2311.10089","version":1},"attestation_state":"computed","paper":{"title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Amit Zohar, Devi Parikh, Oron Ashual, Shelly Sheynin, Uriel Singer, Yaniv Taigman, Yuval Kirstain","submitted_at":"2023-11-16T18:55:58Z","abstract_excerpt":"Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. However, current models in this domain often struggle with accurately executing user instructions. We present Emu Edit, a multi-task image editing model which sets state-of-the-art results in instruction-based image editing. To develop Emu Edit we train it to multi-task across an unprecedented range of tasks, such as region-based editing, free-form editing, and Computer Vision tasks, all of which are formulated as gene"},"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":"2311.10089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-16T18:55:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76184fc9e8e1aac07b2755cce1747fc4d33e1dc968322cd2600974a1933e7566","abstract_canon_sha256":"070ee8eedfe3f816c3672b9d56c03577fd2e5f45d21891ca23669155ff7b406f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:37.481480Z","signature_b64":"IPrkLNqxjccJk9zOIF3SekN1WohcSCs+6IrahMJXOZxzMAnOvJIM+Q9nWllS5QQu/dklnBlU07Kdu6CxEm7IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f63a6a2728799a15a205e86aa89e5fa66147be991506af3908336620c0f454b0","last_reissued_at":"2026-07-05T07:13:37.480991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:37.480991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Amit Zohar, Devi Parikh, Oron Ashual, Shelly Sheynin, Uriel Singer, Yaniv Taigman, Yuval Kirstain","submitted_at":"2023-11-16T18:55:58Z","abstract_excerpt":"Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. However, current models in this domain often struggle with accurately executing user instructions. We present Emu Edit, a multi-task image editing model which sets state-of-the-art results in instruction-based image editing. To develop Emu Edit we train it to multi-task across an unprecedented range of tasks, such as region-based editing, free-form editing, and Computer Vision tasks, all of which are formulated as gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10089","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/2311.10089/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":"2311.10089","created_at":"2026-07-05T07:13:37.481044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10089v1","created_at":"2026-07-05T07:13:37.481044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10089","created_at":"2026-07-05T07:13:37.481044+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Y5GUJZIPGNB","created_at":"2026-07-05T07:13:37.481044+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Y5GUJZIPGNBLIQF","created_at":"2026-07-05T07:13:37.481044+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Y5GUJZI","created_at":"2026-07-05T07:13:37.481044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03206","citing_title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04911","citing_title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04887","citing_title":"HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15742","citing_title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ","json":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ.json","graph_json":"https://pith.science/api/pith-number/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/graph.json","events_json":"https://pith.science/api/pith-number/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/events.json","paper":"https://pith.science/paper/6Y5GUJZI"},"agent_actions":{"view_html":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ","download_json":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ.json","view_paper":"https://pith.science/paper/6Y5GUJZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10089&json=true","fetch_graph":"https://pith.science/api/pith-number/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/action/storage_attestation","attest_author":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/action/author_attestation","sign_citation":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/action/citation_signature","submit_replication":"https://pith.science/pith/6Y5GUJZIPGNBLIQF5BVKRHS7UZ/action/replication_record"}},"created_at":"2026-07-05T07:13:37.481044+00:00","updated_at":"2026-07-05T07:13:37.481044+00:00"}