{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4RVVOFJSSBDPXTQWPKIG64TVK","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":"8ccb436b1b028724580f8924f16ed3efa4df815cb4a68725ac4cd041ab4aefea","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:40:52Z","title_canon_sha256":"fb7d732f9f3c3107dd3aa0ef86856cadf2d32b763dab1ce6d8ee743763346289"},"schema_version":"1.0","source":{"id":"2505.19084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19084","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19084v1","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19084","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"U4RVVOFJSSBD","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"U4RVVOFJSSBDPXTQ","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"U4RVVOFJ","created_at":"2026-07-05T11:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:9d5c8f21ad9a6fa6f0d441a4a199d88addcc409e7ba71d4620e216c68cfb1cfc","target":"graph","created_at":"2026-07-05T11:09:24Z","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/2505.19084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual generation and understanding are two deeply interconnected aspects of human intelligence, yet they have been traditionally treated as separate tasks in machine learning. In this paper, we propose Jodi, a diffusion framework that unifies visual generation and understanding by jointly modeling the image domain and multiple label domains. Specifically, Jodi is built upon a linear diffusion transformer along with a role switch mechanism, which enables it to perform three particular types of tasks: (1) joint generation, where the model simultaneously generates images and multiple labels; (2)","authors_text":"Meina Kan, Shiguang Shan, Xilin Chen, Yifeng Xu, Zhenliang He","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:40:52Z","title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19084","kind":"arxiv","version":1},"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:baf7007fa901b04b0f3921b352da6adf87e32fa52f82a832fa12ada154b7881c","target":"record","created_at":"2026-07-05T11:09:24Z","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":"8ccb436b1b028724580f8924f16ed3efa4df815cb4a68725ac4cd041ab4aefea","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:40:52Z","title_canon_sha256":"fb7d732f9f3c3107dd3aa0ef86856cadf2d32b763dab1ce6d8ee743763346289"},"schema_version":"1.0","source":{"id":"2505.19084","kind":"arxiv","version":1}},"canonical_sha256":"a7235ab8a9948237de70b3d4837b93aa8129cf980047f49d9637b366e830b298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7235ab8a9948237de70b3d4837b93aa8129cf980047f49d9637b366e830b298","first_computed_at":"2026-07-05T11:09:24.622749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:24.622749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Qruu6G2AuYHE6a6KVMQuuRYbyLtWENAZZx/SZpnrb+GVPup+lqnST0zboD0f5P1KLSY2o2I6sm0VDc3qKfuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:24.623305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf7007fa901b04b0f3921b352da6adf87e32fa52f82a832fa12ada154b7881c","sha256:9d5c8f21ad9a6fa6f0d441a4a199d88addcc409e7ba71d4620e216c68cfb1cfc"],"state_sha256":"7f0455296b9718424aa7a4cef8d892a0a6f899cd7a7b0868473af0f8faa1cb35"}