{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K54BE4MWFYR5MGUN32HUNP3CKQ","short_pith_number":"pith:K54BE4MW","schema_version":"1.0","canonical_sha256":"57781271962e23d61a8dde8f46bf62540e97e8581b827cf4b1bd545d4ea05efa","source":{"kind":"arxiv","id":"2507.21033","version":1},"attestation_state":"computed","paper":{"title":"GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cihang Xie, Letian Zhang, Qing Liu, Siwei Yang, Yuhan Wang, Yuyin Zhou","submitted_at":"2025-07-28T17:54:04Z","abstract_excerpt":"Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular ima"},"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":"2507.21033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T17:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"d7cc13e971973782c95f47c22133cc48b84937f9fcb9d83f64d008662f3b6ee8","abstract_canon_sha256":"09bb5d77aa00d52d29c7192bab8b454fb85ffe18fb3f97d2e1bc7d0030c51cac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:30.149339Z","signature_b64":"4YUKO68HlfuIo/f+PHccqq8jcVhctkqTMw7n5lYLX/TWx/6y0ZuBbuLRolsuOTSZ0NvP5cW/ERDh7wzCWyMkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57781271962e23d61a8dde8f46bf62540e97e8581b827cf4b1bd545d4ea05efa","last_reissued_at":"2026-07-05T11:44:30.148910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:30.148910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cihang Xie, Letian Zhang, Qing Liu, Siwei Yang, Yuhan Wang, Yuyin Zhou","submitted_at":"2025-07-28T17:54:04Z","abstract_excerpt":"Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21033","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/2507.21033/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":"2507.21033","created_at":"2026-07-05T11:44:30.148965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21033v1","created_at":"2026-07-05T11:44:30.148965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21033","created_at":"2026-07-05T11:44:30.148965+00:00"},{"alias_kind":"pith_short_12","alias_value":"K54BE4MWFYR5","created_at":"2026-07-05T11:44:30.148965+00:00"},{"alias_kind":"pith_short_16","alias_value":"K54BE4MWFYR5MGUN","created_at":"2026-07-05T11:44:30.148965+00:00"},{"alias_kind":"pith_short_8","alias_value":"K54BE4MW","created_at":"2026-07-05T11:44:30.148965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23041","citing_title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23041","citing_title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04128","citing_title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21090","citing_title":"TextSculptor: Training and Benchmarking Scene Text Editing","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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26583","citing_title":"Emu3.5: Native Multimodal Models are World Learners","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21788","citing_title":"InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05646","citing_title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10954","citing_title":"FineEdit: Fine-Grained Image Edit with Bounding Box Guidance","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06870","citing_title":"RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04911","citing_title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17021","citing_title":"LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04128","citing_title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ","json":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ.json","graph_json":"https://pith.science/api/pith-number/K54BE4MWFYR5MGUN32HUNP3CKQ/graph.json","events_json":"https://pith.science/api/pith-number/K54BE4MWFYR5MGUN32HUNP3CKQ/events.json","paper":"https://pith.science/paper/K54BE4MW"},"agent_actions":{"view_html":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ","download_json":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ.json","view_paper":"https://pith.science/paper/K54BE4MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21033&json=true","fetch_graph":"https://pith.science/api/pith-number/K54BE4MWFYR5MGUN32HUNP3CKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/K54BE4MWFYR5MGUN32HUNP3CKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ/action/storage_attestation","attest_author":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ/action/author_attestation","sign_citation":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ/action/citation_signature","submit_replication":"https://pith.science/pith/K54BE4MWFYR5MGUN32HUNP3CKQ/action/replication_record"}},"created_at":"2026-07-05T11:44:30.148965+00:00","updated_at":"2026-07-05T11:44:30.148965+00:00"}