{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BZCP344GEWPVZQDTWRKMNCRGFN","short_pith_number":"pith:BZCP344G","schema_version":"1.0","canonical_sha256":"0e44fdf386259f5cc073b454c68a262b77b166cf90f8ea620745a49ec5c8f340","source":{"kind":"arxiv","id":"2509.24900","version":2},"attestation_state":"computed","paper":{"title":"OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Haotian Wang, Huanyu Zhang, Liang Wang, Pengfei Wan, Xiaoyan Sun, Xuehai Bai, Yang Shi, Yi-Fan Zhang, Yuanxing Zhang, Zhang Zhang, Zhihong Chen","submitted_at":"2025-09-29T15:11:09Z","abstract_excerpt":"The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fun"},"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":"2509.24900","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-29T15:11:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d54d1f88efb40590640a7aa0bd281e82b5b8f5af6f53d4c156acfe54734f5553","abstract_canon_sha256":"f3927b9799c3c17232cca7a50c95b2b1ace2aa874f8f7b5463e8c38ec494eade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T02:15:38.925990Z","signature_b64":"AVLQvHiSpZEHLnF609lSJ2DmvxrelgbaDbuRoWTB0wiUozfYeEi5v7Q7Bq5Q8YHLONEJrxiQWsMTe1GWeXv9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e44fdf386259f5cc073b454c68a262b77b166cf90f8ea620745a49ec5c8f340","last_reissued_at":"2026-08-18T02:15:38.924333Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T02:15:38.924333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Haotian Wang, Huanyu Zhang, Liang Wang, Pengfei Wan, Xiaoyan Sun, Xuehai Bai, Yang Shi, Yi-Fan Zhang, Yuanxing Zhang, Zhang Zhang, Zhihong Chen","submitted_at":"2025-09-29T15:11:09Z","abstract_excerpt":"The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24900","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/2509.24900/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":"2509.24900","created_at":"2026-08-18T02:15:38.923986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24900v2","created_at":"2026-08-18T02:15:38.923986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24900","created_at":"2026-08-18T02:15:38.923986+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZCP344GEWPV","created_at":"2026-08-18T02:15:38.923986+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZCP344GEWPVZQDT","created_at":"2026-08-18T02:15:38.923986+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZCP344G","created_at":"2026-08-18T02:15:38.923986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"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":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18984","citing_title":"Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12724","citing_title":"Inline Critic Steers Image Editing","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13062","citing_title":"Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02567","citing_title":"Automated In-the-Wild Data Collection for Continual AI Generated Image Detection","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN","json":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN.json","graph_json":"https://pith.science/api/pith-number/BZCP344GEWPVZQDTWRKMNCRGFN/graph.json","events_json":"https://pith.science/api/pith-number/BZCP344GEWPVZQDTWRKMNCRGFN/events.json","paper":"https://pith.science/paper/BZCP344G"},"agent_actions":{"view_html":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN","download_json":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN.json","view_paper":"https://pith.science/paper/BZCP344G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24900&json=true","fetch_graph":"https://pith.science/api/pith-number/BZCP344GEWPVZQDTWRKMNCRGFN/graph.json","fetch_events":"https://pith.science/api/pith-number/BZCP344GEWPVZQDTWRKMNCRGFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN/action/storage_attestation","attest_author":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN/action/author_attestation","sign_citation":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN/action/citation_signature","submit_replication":"https://pith.science/pith/BZCP344GEWPVZQDTWRKMNCRGFN/action/replication_record"}},"created_at":"2026-08-18T02:15:38.923986+00:00","updated_at":"2026-08-18T02:15:38.923986+00:00"}