{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J6LO7OXPYMEPLFT7DT7D2IOXQJ","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":"59d3df9386bcf2167e7a7b8df00ceda6923df8e9a05f94f521831bb954e6d589","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T16:48:22Z","title_canon_sha256":"ae11dc8120e88744319ea3764a69a562b4fdc76fe1805887a07c45b07c514ecd"},"schema_version":"1.0","source":{"id":"2410.22217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22217","created_at":"2026-07-05T09:28:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22217v2","created_at":"2026-07-05T09:28:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22217","created_at":"2026-07-05T09:28:35Z"},{"alias_kind":"pith_short_12","alias_value":"J6LO7OXPYMEP","created_at":"2026-07-05T09:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"J6LO7OXPYMEPLFT7","created_at":"2026-07-05T09:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"J6LO7OXP","created_at":"2026-07-05T09:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:b5805cc040fa52b1c4285b4d6ae00d73e05a74b29e6dc661d6558b1f8c653dcd","target":"graph","created_at":"2026-07-05T09:28:35Z","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/2410.22217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing interest in extending this success to vision foundation models. In this survey, we review the recent advances and discuss future directions for autoregressive vision foundation models. First, we present the trend for next generation of vision foundation models, i.e., unifying both understanding and generation in vision tasks. We then analyze the limitations of existing vision foundation models, and present a formal ","authors_text":"Duo Su, Guoqi Li, Lei Ma, Mingyang Zhao, Ruohua Shi, Shanghang Zhang, Shenghao Xie, Shilong Liu, Wenqiang Zu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T16:48:22Z","title":"Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22217","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":"sha256:67ad2c02e171556af552da4017d264f612502e47890c28208a60cf4deead235e","target":"record","created_at":"2026-07-05T09:28:35Z","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":"59d3df9386bcf2167e7a7b8df00ceda6923df8e9a05f94f521831bb954e6d589","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T16:48:22Z","title_canon_sha256":"ae11dc8120e88744319ea3764a69a562b4fdc76fe1805887a07c45b07c514ecd"},"schema_version":"1.0","source":{"id":"2410.22217","kind":"arxiv","version":2}},"canonical_sha256":"4f96efbaefc308f5967f1cfe3d21d78272d991ba1ae6b2ac71d3324424718388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f96efbaefc308f5967f1cfe3d21d78272d991ba1ae6b2ac71d3324424718388","first_computed_at":"2026-07-05T09:28:35.814795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:35.814795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1cq4cutO6qz1uQ2RZR3eVoJiEUPDLA6f17NYwUDvOVGB4GioYgoZrKo+cOgGI4xhUhaFV3nClNzhXRaP64rGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:35.815253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67ad2c02e171556af552da4017d264f612502e47890c28208a60cf4deead235e","sha256:b5805cc040fa52b1c4285b4d6ae00d73e05a74b29e6dc661d6558b1f8c653dcd"],"state_sha256":"3ae76307432290d66f59aadbd1c5bd66a9e1a74bc6d49fcae6b2c0049282c5dc"}