{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L6JO7INTYQ2IXELNOEN7MLWQGE","short_pith_number":"pith:L6JO7INT","schema_version":"1.0","canonical_sha256":"5f92efa1b3c4348b916d711bf62ed03132f6374077a0fae2dbb7a6d510062dd4","source":{"kind":"arxiv","id":"2504.02782","version":3},"attestation_state":"computed","paper":{"title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conghui He, Jun He, Junyan Ye, Kaiqing Lin, Li Yuan, Shenghai Yuan, Weijia Li, Xiangyang He, Zhiyuan Yan, Zilong Huang","submitted_at":"2025-04-03T17:23:16Z","abstract_excerpt":"The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the community. This technical report presents the first-look evaluation benchmark (named GPT-ImgEval), quantitatively and qualitatively diagnosing GPT-4o's performance across three critical dimensions: (1) generation quality, (2) editing proficiency, and (3) world knowledge-informed semantic synthesis. Across all three tasks, GPT-4o demonstrates strong performance, significantly surpassing existing methods in both image genera"},"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":"2504.02782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T17:23:16Z","cross_cats_sorted":[],"title_canon_sha256":"dc1247d3a1a5820723f0d40402b36b983ba91321d5ab3ca06f1e1ed7e57e140d","abstract_canon_sha256":"1bb5ecdef447207f796b36d13ad241604a8858f7b37f68767b4bc83c80ffec6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:35.578931Z","signature_b64":"79xgRotMcZMV7Nf/FPOUZomSEx0b1/JB7jrPof5GjAjVjJzj/g+Kc+Ak7zQ8CxEGUFxLgfFWJaHrxiY6lsSeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f92efa1b3c4348b916d711bf62ed03132f6374077a0fae2dbb7a6d510062dd4","last_reissued_at":"2026-07-05T10:57:35.578417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:35.578417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conghui He, Jun He, Junyan Ye, Kaiqing Lin, Li Yuan, Shenghai Yuan, Weijia Li, Xiangyang He, Zhiyuan Yan, Zilong Huang","submitted_at":"2025-04-03T17:23:16Z","abstract_excerpt":"The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the community. This technical report presents the first-look evaluation benchmark (named GPT-ImgEval), quantitatively and qualitatively diagnosing GPT-4o's performance across three critical dimensions: (1) generation quality, (2) editing proficiency, and (3) world knowledge-informed semantic synthesis. Across all three tasks, GPT-4o demonstrates strong performance, significantly surpassing existing methods in both image genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02782","kind":"arxiv","version":3},"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/2504.02782/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":"2504.02782","created_at":"2026-07-05T10:57:35.578478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02782v3","created_at":"2026-07-05T10:57:35.578478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02782","created_at":"2026-07-05T10:57:35.578478+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6JO7INTYQ2I","created_at":"2026-07-05T10:57:35.578478+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6JO7INTYQ2IXELN","created_at":"2026-07-05T10:57:35.578478+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6JO7INT","created_at":"2026-07-05T10:57:35.578478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18518","citing_title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19985","citing_title":"Vision-Reasoning-Guided Occlusion Removal from Light Fields","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18249","citing_title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22126","citing_title":"AesFormer: Transform Everyday Photos into Beautiful Memories","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2504.06256","citing_title":"Transfer between Modalities with MetaQueries","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12112","citing_title":"When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2505.09568","citing_title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05470","citing_title":"Flow-GRPO: Training Flow Matching Models via Online RL","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18518","citing_title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE","json":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE.json","graph_json":"https://pith.science/api/pith-number/L6JO7INTYQ2IXELNOEN7MLWQGE/graph.json","events_json":"https://pith.science/api/pith-number/L6JO7INTYQ2IXELNOEN7MLWQGE/events.json","paper":"https://pith.science/paper/L6JO7INT"},"agent_actions":{"view_html":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE","download_json":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE.json","view_paper":"https://pith.science/paper/L6JO7INT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02782&json=true","fetch_graph":"https://pith.science/api/pith-number/L6JO7INTYQ2IXELNOEN7MLWQGE/graph.json","fetch_events":"https://pith.science/api/pith-number/L6JO7INTYQ2IXELNOEN7MLWQGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE/action/storage_attestation","attest_author":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE/action/author_attestation","sign_citation":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE/action/citation_signature","submit_replication":"https://pith.science/pith/L6JO7INTYQ2IXELNOEN7MLWQGE/action/replication_record"}},"created_at":"2026-07-05T10:57:35.578478+00:00","updated_at":"2026-07-05T10:57:35.578478+00:00"}