{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F35YA67XCBHGBDV464MGNBH46I","short_pith_number":"pith:F35YA67X","schema_version":"1.0","canonical_sha256":"2efb807bf7104e608ebcf7186684fcf20b503916d3d6862d6f8fd42761a8315d","source":{"kind":"arxiv","id":"2405.04007","version":1},"attestation_state":"computed","paper":{"title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Sijie Zhao, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2024-05-07T04:55:47Z","abstract_excerpt":"In this technical report, we introduce SEED-Data-Edit: a unique hybrid dataset for instruction-guided image editing, which aims to facilitate image manipulation using open-form language. SEED-Data-Edit is composed of three distinct types of data: (1) High-quality editing data produced by an automated pipeline, ensuring a substantial volume of diverse image editing pairs. (2) Real-world scenario data collected from the internet, which captures the intricacies of user intentions for promoting the practical application of image editing in the real world. (3) High-precision multi-turn editing data"},"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":"2405.04007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T04:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"a323a3e168f99f415350c16f58b1ade9bd582ecf204a9c284546b84dfb120722","abstract_canon_sha256":"4695967b4f91865f88218b63e508734735111446ce6e9981eb58f951656e7bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:30.388611Z","signature_b64":"OiwFLpPVjUaFZcfHmXTs43LnLDxxySt7i+oEMpT1BENWlU2z0blgkHIARqtyRYjwqS2eORiXPrgAmUbfCyfmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2efb807bf7104e608ebcf7186684fcf20b503916d3d6862d6f8fd42761a8315d","last_reissued_at":"2026-07-05T08:16:30.388172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:30.388172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Sijie Zhao, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2024-05-07T04:55:47Z","abstract_excerpt":"In this technical report, we introduce SEED-Data-Edit: a unique hybrid dataset for instruction-guided image editing, which aims to facilitate image manipulation using open-form language. SEED-Data-Edit is composed of three distinct types of data: (1) High-quality editing data produced by an automated pipeline, ensuring a substantial volume of diverse image editing pairs. (2) Real-world scenario data collected from the internet, which captures the intricacies of user intentions for promoting the practical application of image editing in the real world. (3) High-precision multi-turn editing data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04007","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/2405.04007/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":"2405.04007","created_at":"2026-07-05T08:16:30.388229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04007v1","created_at":"2026-07-05T08:16:30.388229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04007","created_at":"2026-07-05T08:16:30.388229+00:00"},{"alias_kind":"pith_short_12","alias_value":"F35YA67XCBHG","created_at":"2026-07-05T08:16:30.388229+00:00"},{"alias_kind":"pith_short_16","alias_value":"F35YA67XCBHGBDV4","created_at":"2026-07-05T08:16:30.388229+00:00"},{"alias_kind":"pith_short_8","alias_value":"F35YA67X","created_at":"2026-07-05T08:16:30.388229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09156","citing_title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00931","citing_title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23518","citing_title":"VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18871","citing_title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01986","citing_title":"Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20360","citing_title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13609","citing_title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10954","citing_title":"FineEdit: Fine-Grained Image Edit with Bounding Box Guidance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08029","citing_title":"STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04911","citing_title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I","json":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I.json","graph_json":"https://pith.science/api/pith-number/F35YA67XCBHGBDV464MGNBH46I/graph.json","events_json":"https://pith.science/api/pith-number/F35YA67XCBHGBDV464MGNBH46I/events.json","paper":"https://pith.science/paper/F35YA67X"},"agent_actions":{"view_html":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I","download_json":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I.json","view_paper":"https://pith.science/paper/F35YA67X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04007&json=true","fetch_graph":"https://pith.science/api/pith-number/F35YA67XCBHGBDV464MGNBH46I/graph.json","fetch_events":"https://pith.science/api/pith-number/F35YA67XCBHGBDV464MGNBH46I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I/action/storage_attestation","attest_author":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I/action/author_attestation","sign_citation":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I/action/citation_signature","submit_replication":"https://pith.science/pith/F35YA67XCBHGBDV464MGNBH46I/action/replication_record"}},"created_at":"2026-07-05T08:16:30.388229+00:00","updated_at":"2026-07-05T08:16:30.388229+00:00"}