{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2AAM6DI2XCIMQ7JSTTWLWTG5QE","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":"0d736e082142ed71db50c9f4b2cb9adeb809b132dfb276e30cd19193ddd3cc09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T08:35:09Z","title_canon_sha256":"a611d4d404ba4ec39384a982721b8fd983a0d181e005ab597ce9ef727e5d4e87"},"schema_version":"1.0","source":{"id":"2607.24157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24157","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24157v1","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24157","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"2AAM6DI2XCIM","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"2AAM6DI2XCIMQ7JS","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"2AAM6DI2","created_at":"2026-07-28T01:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:5d81c0f1b164e16819c434d0e6d53433ec0ad73785346f15d51a90279ca1a440","target":"graph","created_at":"2026-07-28T01:23:47Z","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/2607.24157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface. While diffusion-based systems dominate UVG due to strong quality and controllability, their iterative sampling incurs substantial inference latency, limiting practical deployment. To address these limitations, we propose UniGen-AR, a framework that pairs a general-purpose multi-modal la","authors_text":"Anurag Bagchi, Martial Hebert, Nupur Kumari, Pavel Tokmakov, Yu-Xiong Wang, Zhen Zhu, Zhipeng Bao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T08:35:09Z","title":"UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24157","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":"sha256:77fbcd406802bfe177bd13c5b9f7c79401e543e24a12ddc778abefab33c7cc0c","target":"record","created_at":"2026-07-28T01:23:47Z","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":"0d736e082142ed71db50c9f4b2cb9adeb809b132dfb276e30cd19193ddd3cc09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T08:35:09Z","title_canon_sha256":"a611d4d404ba4ec39384a982721b8fd983a0d181e005ab597ce9ef727e5d4e87"},"schema_version":"1.0","source":{"id":"2607.24157","kind":"arxiv","version":1}},"canonical_sha256":"d000cf0d1ab890c87d329cecbb4cdd8106f6e74d3d649a6e60ef366aeec0d1ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d000cf0d1ab890c87d329cecbb4cdd8106f6e74d3d649a6e60ef366aeec0d1ab","first_computed_at":"2026-07-28T01:23:47.818027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:47.818027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEjH/I/H95W7pzIM2UUHg2u2iaFaNYTVMIGyrMWy1I72SX2TK78ecbmXnWfrINyPD+0g+e+aFV44P+deIEfGCw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:47.818859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77fbcd406802bfe177bd13c5b9f7c79401e543e24a12ddc778abefab33c7cc0c","sha256:5d81c0f1b164e16819c434d0e6d53433ec0ad73785346f15d51a90279ca1a440"],"state_sha256":"f9975e9a244e2fcb61c9d74ada5f4b80314dcc02aa37e8bb158893c4df60bdc1"}