{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R5UDKTPTYBNYTROJBECV45AWHU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3aa0e48c178080202e6972ce983d68888a66c7b7828fff17c4859754aaa0ca47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T12:17:04Z","title_canon_sha256":"834f68cb41708af5f657b8d262e22b72e4726accd5101fa638a74078a2e77a91"},"schema_version":"1.0","source":{"id":"2505.13031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13031","created_at":"2026-07-05T11:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13031v2","created_at":"2026-07-05T11:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13031","created_at":"2026-07-05T11:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"R5UDKTPTYBNY","created_at":"2026-07-05T11:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"R5UDKTPTYBNYTROJ","created_at":"2026-07-05T11:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"R5UDKTPT","created_at":"2026-07-05T11:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:9f2b6215f8b5eacfa8ca9ab22423059909c56105c51b55058dd5006969d089f3","target":"graph","created_at":"2026-07-05T11:19:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation through reinforcement learning. MindOmni leverages a three-phase training strategy: i) design of a unified vision language model with a decoder-only diffusion module, ii) supervised fine-tuning with Chain-of-Thought (CoT) instruction data, and iii) our proposed Reasoning Generation Policy Optimization (RGPO) algorithm, utilizing multimodal feedback to effect","authors_text":"Lin Song, Wei Huang, Xiaojuan Qi, Xiu Li, Yicheng Xiao, Yingmin Luo, Ying Shan, Yukang Chen, Yukang Gan, Yuxin Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T12:17:04Z","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13031","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:792769f32e3a6a751e078b64ee11893ccf948247a6cac44444f7c97524c489e0","target":"record","created_at":"2026-07-05T11:19:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3aa0e48c178080202e6972ce983d68888a66c7b7828fff17c4859754aaa0ca47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T12:17:04Z","title_canon_sha256":"834f68cb41708af5f657b8d262e22b72e4726accd5101fa638a74078a2e77a91"},"schema_version":"1.0","source":{"id":"2505.13031","kind":"arxiv","version":2}},"canonical_sha256":"8f68354df3c05b89c5c909055e74163d13b426e7b174e1b1bfa301de942bfcc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f68354df3c05b89c5c909055e74163d13b426e7b174e1b1bfa301de942bfcc7","first_computed_at":"2026-07-05T11:19:52.743459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:52.743459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sSM4DqjYNE3OSBBhOy5m/Tmoht3hHUBzndOqNU+MX7xdz+xUQf/B1nZH+zAC+Y6qpFfE9GyXBXw0ieelOx/eDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:52.743967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792769f32e3a6a751e078b64ee11893ccf948247a6cac44444f7c97524c489e0","sha256:9f2b6215f8b5eacfa8ca9ab22423059909c56105c51b55058dd5006969d089f3"],"state_sha256":"c9468bea6a4b709bee2d1b78701f7c15e2ce948a2e80bb824c0b50204bdde71b"}