{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U4RVVOFJSSBDPXTQWPKIG64TVK","short_pith_number":"pith:U4RVVOFJ","canonical_record":{"source":{"id":"2505.19084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:40:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb7d732f9f3c3107dd3aa0ef86856cadf2d32b763dab1ce6d8ee743763346289","abstract_canon_sha256":"8ccb436b1b028724580f8924f16ed3efa4df815cb4a68725ac4cd041ab4aefea"},"schema_version":"1.0"},"canonical_sha256":"a7235ab8a9948237de70b3d4837b93aa8129cf980047f49d9637b366e830b298","source":{"kind":"arxiv","id":"2505.19084","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U4RVVOFJSSBDPXTQWPKIG64TVK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:40:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb7d732f9f3c3107dd3aa0ef86856cadf2d32b763dab1ce6d8ee743763346289","abstract_canon_sha256":"8ccb436b1b028724580f8924f16ed3efa4df815cb4a68725ac4cd041ab4aefea"},"schema_version":"1.0"},"canonical_sha256":"a7235ab8a9948237de70b3d4837b93aa8129cf980047f49d9637b366e830b298","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:24.623305Z","signature_b64":"/Qruu6G2AuYHE6a6KVMQuuRYbyLtWENAZZx/SZpnrb+GVPup+lqnST0zboD0f5P1KLSY2o2I6sm0VDc3qKfuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7235ab8a9948237de70b3d4837b93aa8129cf980047f49d9637b366e830b298","last_reissued_at":"2026-07-05T11:09:24.622749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:24.622749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19084","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oJ9bDH7WF0soWble8XsMhx1F0p2o1eoRQCpsyOglzV3z7VpDad9wMZarnOCaP2BaMFsgo44BKUqLeI7l6K4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:13:05.863649Z"},"content_sha256":"baf7007fa901b04b0f3921b352da6adf87e32fa52f82a832fa12ada154b7881c","schema_version":"1.0","event_id":"sha256:baf7007fa901b04b0f3921b352da6adf87e32fa52f82a832fa12ada154b7881c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U4RVVOFJSSBDPXTQWPKIG64TVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Meina Kan, Shiguang Shan, Xilin Chen, Yifeng Xu, Zhenliang He","submitted_at":"2025-05-25T10:40:52Z","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)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19084","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/2505.19084/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSgVqOF3BcOVD3l7X4E5C4iVlWM5AC7dnp99DVGeUBtTNBu8Cmy093AINiL4+s2eyU+egO1Wy4HLuFvZkV5wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:13:05.864186Z"},"content_sha256":"9d5c8f21ad9a6fa6f0d441a4a199d88addcc409e7ba71d4620e216c68cfb1cfc","schema_version":"1.0","event_id":"sha256:9d5c8f21ad9a6fa6f0d441a4a199d88addcc409e7ba71d4620e216c68cfb1cfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/bundle.json","state_url":"https://pith.science/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T00:13:05Z","links":{"resolver":"https://pith.science/pith/U4RVVOFJSSBDPXTQWPKIG64TVK","bundle":"https://pith.science/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/bundle.json","state":"https://pith.science/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4RVVOFJSSBDPXTQWPKIG64TVK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1kFyMdjBiCTPs97YPnq+tOxN98s5JKFF3skC3p3wyeUbvEDtCgwc/Aw2E1h6Ofqur6sIMu1lI4VGWfjIEsxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:13:05.868233Z","bundle_sha256":"746ce46803c6fca2e2096667454e244fa9dc87ec61ea7ab2036cf6a72125978d"}}