{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBCTCVX57JM6VM2BS66PULMRKG","short_pith_number":"pith:RBCTCVX5","schema_version":"1.0","canonical_sha256":"88453156fdfa59eab34197bcfa2d9151b7523a0187ef2b8961eae9c9bec8d4a9","source":{"kind":"arxiv","id":"2404.09990","version":1},"attestation_state":"computed","paper":{"title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cihang Xie, Heng Wang, Mude Hui, Peng Wang, Siwei Yang, Yichun Shi, Yuyin Zhou","submitted_at":"2024-04-15T17:59:31Z","abstract_excerpt":"This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose tw"},"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":"2404.09990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:59:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a51b8753004b951e1e930ad6775906f50181711d64d843af5055d33c8c598e2","abstract_canon_sha256":"720d6d6c4c796cfa8146ad6f55828615f69724dff6bbd4de524d3a23135c8beb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:13.957095Z","signature_b64":"didLruIj8ESjj0RODaA9rD8CpGGIoaB4nQOcHOAilNAWufVCvhx/ACABhxl3Rzeg1Ocj2aBnkd/6RmMfSP04Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88453156fdfa59eab34197bcfa2d9151b7523a0187ef2b8961eae9c9bec8d4a9","last_reissued_at":"2026-07-05T08:08:13.956581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:13.956581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cihang Xie, Heng Wang, Mude Hui, Peng Wang, Siwei Yang, Yichun Shi, Yuyin Zhou","submitted_at":"2024-04-15T17:59:31Z","abstract_excerpt":"This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09990","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/2404.09990/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":"2404.09990","created_at":"2026-07-05T08:08:13.956645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09990v1","created_at":"2026-07-05T08:08:13.956645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09990","created_at":"2026-07-05T08:08:13.956645+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBCTCVX57JM6","created_at":"2026-07-05T08:08:13.956645+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBCTCVX57JM6VM2B","created_at":"2026-07-05T08:08:13.956645+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBCTCVX5","created_at":"2026-07-05T08:08:13.956645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07051","citing_title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25445","citing_title":"C3-Bench: A Context-Aware Change Captioning Benchmark","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23221","citing_title":"RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11188","citing_title":"ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01985","citing_title":"MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24762","citing_title":"4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":20,"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":29,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01908","citing_title":"Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning","ref_index":6,"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":9,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13609","citing_title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11818","citing_title":"RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12904","citing_title":"A Sanity Check on Composed Image Retrieval","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10454","citing_title":"AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10954","citing_title":"FineEdit: Fine-Grained Image Edit with Bounding Box Guidance","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08213","citing_title":"EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07457","citing_title":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG","json":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG.json","graph_json":"https://pith.science/api/pith-number/RBCTCVX57JM6VM2BS66PULMRKG/graph.json","events_json":"https://pith.science/api/pith-number/RBCTCVX57JM6VM2BS66PULMRKG/events.json","paper":"https://pith.science/paper/RBCTCVX5"},"agent_actions":{"view_html":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG","download_json":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG.json","view_paper":"https://pith.science/paper/RBCTCVX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09990&json=true","fetch_graph":"https://pith.science/api/pith-number/RBCTCVX57JM6VM2BS66PULMRKG/graph.json","fetch_events":"https://pith.science/api/pith-number/RBCTCVX57JM6VM2BS66PULMRKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG/action/storage_attestation","attest_author":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG/action/author_attestation","sign_citation":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG/action/citation_signature","submit_replication":"https://pith.science/pith/RBCTCVX57JM6VM2BS66PULMRKG/action/replication_record"}},"created_at":"2026-07-05T08:08:13.956645+00:00","updated_at":"2026-07-05T08:08:13.956645+00:00"}