{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5L5UADVK6RXSJ73QMGKU2ZEPFM","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":"28fce48001bef4f4c0e450d023503a946335bbdeaaf0595054e4953f2f01e44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T15:37:17Z","title_canon_sha256":"efe54a506e01ff60310a625a7dd022739e2c3fc20cbd043b65c972494114775a"},"schema_version":"1.0","source":{"id":"2503.20644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20644","created_at":"2026-07-05T10:39:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20644v1","created_at":"2026-07-05T10:39:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20644","created_at":"2026-07-05T10:39:41Z"},{"alias_kind":"pith_short_12","alias_value":"5L5UADVK6RXS","created_at":"2026-07-05T10:39:41Z"},{"alias_kind":"pith_short_16","alias_value":"5L5UADVK6RXSJ73Q","created_at":"2026-07-05T10:39:41Z"},{"alias_kind":"pith_short_8","alias_value":"5L5UADVK","created_at":"2026-07-05T10:39:41Z"}],"graph_snapshots":[{"event_id":"sha256:3891d313c606eea047f87b802a697290cd2794d7d5b5a45a52709faa29da72a1","target":"graph","created_at":"2026-07-05T10:39:41Z","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/2503.20644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks. In this paper, we introduce MMGen, a unified framework that integrates multiple generative tasks into a single diffusion model. This includes: (1) multi-modal category-conditioned generation, where multi-modal outputs are generated simultaneously through a single inference process, given category information; (2) multi-modal visual understanding, which accurately predicts depth, surface normals, and segment","authors_text":"Changhu Wang, Dongdong Yu, Hao Pan, Jiepeng Wang, Wenping Wang, Yuan Liu, Zhaoqing Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T15:37:17Z","title":"MMGen: Unified Multi-modal Image Generation and Understanding in One Go"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20644","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":"sha256:5bc92a930b67f17e27d08fa0f620f7464bc6c977306e8bcefc3d28e48f334c2c","target":"record","created_at":"2026-07-05T10:39:41Z","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":"28fce48001bef4f4c0e450d023503a946335bbdeaaf0595054e4953f2f01e44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T15:37:17Z","title_canon_sha256":"efe54a506e01ff60310a625a7dd022739e2c3fc20cbd043b65c972494114775a"},"schema_version":"1.0","source":{"id":"2503.20644","kind":"arxiv","version":1}},"canonical_sha256":"eafb400eaaf46f24ff7061954d648f2b26873bc0c0f0a7d1739c3d9172fc372c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eafb400eaaf46f24ff7061954d648f2b26873bc0c0f0a7d1739c3d9172fc372c","first_computed_at":"2026-07-05T10:39:41.763789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:41.763789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BTgH1NAds5eCViD/fsBWHlrYl2tG02b+c+3OJ2gYd+Kwdx1zJlufyM96aUzafp/sA9sua7NjU4B8NP793XAzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:41.764373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bc92a930b67f17e27d08fa0f620f7464bc6c977306e8bcefc3d28e48f334c2c","sha256:3891d313c606eea047f87b802a697290cd2794d7d5b5a45a52709faa29da72a1"],"state_sha256":"0e9a5254ccbab3a87cc12b9185d7fc6f2430e63ab79e7c69e7efe692bd07643d"}