{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OCC73BNSMMKVAE3H5INKUHIQTH","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":"0eea69fdef1c0ea9780c8e7abcfd2c5672756cc4a4300d373cb727c8f7568e4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T03:51:53Z","title_canon_sha256":"52460d1c058b287d5074d84913e978ee0c8c2a41c346e2fe9b5dc2fda73d455b"},"schema_version":"1.0","source":{"id":"2608.03084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03084","created_at":"2026-08-05T00:45:18Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03084v1","created_at":"2026-08-05T00:45:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03084","created_at":"2026-08-05T00:45:18Z"},{"alias_kind":"pith_short_12","alias_value":"OCC73BNSMMKV","created_at":"2026-08-05T00:45:18Z"},{"alias_kind":"pith_short_16","alias_value":"OCC73BNSMMKVAE3H","created_at":"2026-08-05T00:45:18Z"},{"alias_kind":"pith_short_8","alias_value":"OCC73BNS","created_at":"2026-08-05T00:45:18Z"}],"graph_snapshots":[{"event_id":"sha256:c004a8970d398caf547868756339ab62bbb6255ab3ea71c8b353e758c1def2de","target":"graph","created_at":"2026-08-05T00:45:18Z","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/2608.03084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output formats, with limited scalability. Can video generation instead provide a shared predictor? We introduce SUV, a unified end-to-end driving framework that casts future Scene Understanding as Video generation using a pretrained video foundation model. SUV models future appearance, semantics, relative depth, and instance-level dynamics as video streams with a shared video expert, without stream-specific visual prediction heads. Through joint video-act","authors_text":"Hang Xu, Jiacheng Fu, Jiangtong Zhu, Jianhua Han, Jianru Xue, Jianwu Fang, Meng Tian, Yibo Yuan, Yi Li, Zhiwei Xiong, Zhuohan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T03:51:53Z","title":"SUV: Future Scene Understanding as Video Generation for End-to-End Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03084","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":"sha256:1b1491b5bb1b8440b5fbbf345968a72ca0ea15e512e4ea8304b69ef6e871ffe6","target":"record","created_at":"2026-08-05T00:45:18Z","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":"0eea69fdef1c0ea9780c8e7abcfd2c5672756cc4a4300d373cb727c8f7568e4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T03:51:53Z","title_canon_sha256":"52460d1c058b287d5074d84913e978ee0c8c2a41c346e2fe9b5dc2fda73d455b"},"schema_version":"1.0","source":{"id":"2608.03084","kind":"arxiv","version":1}},"canonical_sha256":"7085fd85b26315501367ea1aaa1d1099d4cba9bbf3a545f895a17fa3318a3d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7085fd85b26315501367ea1aaa1d1099d4cba9bbf3a545f895a17fa3318a3d34","first_computed_at":"2026-08-05T00:45:18.769363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:45:18.769363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2J/Me34TGS0PohCNu0dmRYLcB5gyW0HPEpNMnlRYyXVKYZrLK2jD1NozVURTSgldnWr7qvnA1qolNFY15ImACA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:45:18.772099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b1491b5bb1b8440b5fbbf345968a72ca0ea15e512e4ea8304b69ef6e871ffe6","sha256:c004a8970d398caf547868756339ab62bbb6255ab3ea71c8b353e758c1def2de"],"state_sha256":"c7c17e93765249f218c24b004fa3215a5efa882d33aad72e0d5fb191febda661"}