{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEDLG7XLD6VHBK3LF5ACARODX7","short_pith_number":"pith:FEDLG7XL","schema_version":"1.0","canonical_sha256":"2906b37eeb1faa70ab6b2f402045c3bff347c90d6f1500a4eed704a118d97b5a","source":{"kind":"arxiv","id":"2506.18095","version":1},"attestation_state":"computed","paper":{"title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benyou Wang, Junying Chen, Ke Ji, Pengcheng Chen, Shunian Chen, Xidong Wang, Yunjin Yang, Zhenyang Cai","submitted_at":"2025-06-22T16:51:09Z","abstract_excerpt":"Recent advances in multimodal generative models have unlocked photorealistic, instruction-aligned image generation, yet leading systems like GPT-4o-Image remain proprietary and inaccessible. To democratize these capabilities, we present ShareGPT-4o-Image, the first dataset comprising 45K text-to-image and 46K text-and-image-to-image data, all synthesized using GPT-4o's image generation capabilities for distilling its advanced image generation abilities. Leveraging this dataset, we develop Janus-4o, a multimodal large language model capable of both text-to-image and text-and-image-to-image gene"},"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":"2506.18095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T16:51:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8bec2c404ea6dd523d2c5464029c9e7de4731ee96581d30b7c502094fde4d4ec","abstract_canon_sha256":"d538c69fc33545a77272f181f1fba22efd6b426d3d3ad591d27f424fb91ae77a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:28.424131Z","signature_b64":"5wFKMGH8WG163UQZVaPC4wkfHixANQ69DAvl1JDJdtpHgKc8+EoaZJvsMFRi2eqe6EK5Ik2BxbZ91V9C8TzoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2906b37eeb1faa70ab6b2f402045c3bff347c90d6f1500a4eed704a118d97b5a","last_reissued_at":"2026-07-05T11:25:28.423672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:28.423672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benyou Wang, Junying Chen, Ke Ji, Pengcheng Chen, Shunian Chen, Xidong Wang, Yunjin Yang, Zhenyang Cai","submitted_at":"2025-06-22T16:51:09Z","abstract_excerpt":"Recent advances in multimodal generative models have unlocked photorealistic, instruction-aligned image generation, yet leading systems like GPT-4o-Image remain proprietary and inaccessible. To democratize these capabilities, we present ShareGPT-4o-Image, the first dataset comprising 45K text-to-image and 46K text-and-image-to-image data, all synthesized using GPT-4o's image generation capabilities for distilling its advanced image generation abilities. Leveraging this dataset, we develop Janus-4o, a multimodal large language model capable of both text-to-image and text-and-image-to-image gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18095","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/2506.18095/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":"2506.18095","created_at":"2026-07-05T11:25:28.423719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18095v1","created_at":"2026-07-05T11:25:28.423719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18095","created_at":"2026-07-05T11:25:28.423719+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEDLG7XLD6VH","created_at":"2026-07-05T11:25:28.423719+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEDLG7XLD6VHBK3L","created_at":"2026-07-05T11:25:28.423719+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEDLG7XL","created_at":"2026-07-05T11:25:28.423719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24849","citing_title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","ref_index":56,"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":7,"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":8,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11188","citing_title":"ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04457","citing_title":"Imagine Before You Draw: Visual Prompt Engineering for Image Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31326","citing_title":"Bridging Video Understanding and Generation in a Unified Framework","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29814","citing_title":"Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26108","citing_title":"Reinforcing Few-step Generators via Reward-Tilted Distribution Matching","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21100","citing_title":"NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding","ref_index":8,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26583","citing_title":"Emu3.5: Native Multimodal Models are World Learners","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22663","citing_title":"AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06663","citing_title":"PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15332","citing_title":"Automating Crash Diagram Generation Using Vision-Language Models: A Case Study on Multi-Lane Roundabouts","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12724","citing_title":"Inline Critic Steers Image Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08354","citing_title":"Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05646","citing_title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18168","citing_title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17736","citing_title":"IncreFA: Breaking the Static Wall of Generative Model Attribution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19009","citing_title":"Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7","json":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7.json","graph_json":"https://pith.science/api/pith-number/FEDLG7XLD6VHBK3LF5ACARODX7/graph.json","events_json":"https://pith.science/api/pith-number/FEDLG7XLD6VHBK3LF5ACARODX7/events.json","paper":"https://pith.science/paper/FEDLG7XL"},"agent_actions":{"view_html":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7","download_json":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7.json","view_paper":"https://pith.science/paper/FEDLG7XL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18095&json=true","fetch_graph":"https://pith.science/api/pith-number/FEDLG7XLD6VHBK3LF5ACARODX7/graph.json","fetch_events":"https://pith.science/api/pith-number/FEDLG7XLD6VHBK3LF5ACARODX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7/action/storage_attestation","attest_author":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7/action/author_attestation","sign_citation":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7/action/citation_signature","submit_replication":"https://pith.science/pith/FEDLG7XLD6VHBK3LF5ACARODX7/action/replication_record"}},"created_at":"2026-07-05T11:25:28.423719+00:00","updated_at":"2026-07-05T11:25:28.423719+00:00"}