{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OCC73BNSMMKVAE3H5INKUHIQTH","short_pith_number":"pith:OCC73BNS","schema_version":"1.0","canonical_sha256":"7085fd85b26315501367ea1aaa1d1099d4cba9bbf3a545f895a17fa3318a3d34","source":{"kind":"arxiv","id":"2608.03084","version":1},"attestation_state":"computed","paper":{"title":"SUV: Future Scene Understanding as Video Generation for End-to-End Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Jiacheng Fu, Jiangtong Zhu, Jianhua Han, Jianru Xue, Jianwu Fang, Meng Tian, Yibo Yuan, Yi Li, Zhiwei Xiong, Zhuohan Liu","submitted_at":"2026-08-04T03:51:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T03:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"52460d1c058b287d5074d84913e978ee0c8c2a41c346e2fe9b5dc2fda73d455b","abstract_canon_sha256":"0eea69fdef1c0ea9780c8e7abcfd2c5672756cc4a4300d373cb727c8f7568e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:45:18.772099Z","signature_b64":"2J/Me34TGS0PohCNu0dmRYLcB5gyW0HPEpNMnlRYyXVKYZrLK2jD1NozVURTSgldnWr7qvnA1qolNFY15ImACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7085fd85b26315501367ea1aaa1d1099d4cba9bbf3a545f895a17fa3318a3d34","last_reissued_at":"2026-08-05T00:45:18.769363Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:45:18.769363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUV: Future Scene Understanding as Video Generation for End-to-End Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Jiacheng Fu, Jiangtong Zhu, Jianhua Han, Jianru Xue, Jianwu Fang, Meng Tian, Yibo Yuan, Yi Li, Zhiwei Xiong, Zhuohan Liu","submitted_at":"2026-08-04T03:51:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03084","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/2608.03084/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03084","created_at":"2026-08-05T00:45:18.770532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03084v1","created_at":"2026-08-05T00:45:18.770532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03084","created_at":"2026-08-05T00:45:18.770532+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCC73BNSMMKV","created_at":"2026-08-05T00:45:18.770532+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCC73BNSMMKVAE3H","created_at":"2026-08-05T00:45:18.770532+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCC73BNS","created_at":"2026-08-05T00:45:18.770532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH","json":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH.json","graph_json":"https://pith.science/api/pith-number/OCC73BNSMMKVAE3H5INKUHIQTH/graph.json","events_json":"https://pith.science/api/pith-number/OCC73BNSMMKVAE3H5INKUHIQTH/events.json","paper":"https://pith.science/paper/OCC73BNS"},"agent_actions":{"view_html":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH","download_json":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH.json","view_paper":"https://pith.science/paper/OCC73BNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03084&json=true","fetch_graph":"https://pith.science/api/pith-number/OCC73BNSMMKVAE3H5INKUHIQTH/graph.json","fetch_events":"https://pith.science/api/pith-number/OCC73BNSMMKVAE3H5INKUHIQTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH/action/storage_attestation","attest_author":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH/action/author_attestation","sign_citation":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH/action/citation_signature","submit_replication":"https://pith.science/pith/OCC73BNSMMKVAE3H5INKUHIQTH/action/replication_record"}},"created_at":"2026-08-05T00:45:18.770532+00:00","updated_at":"2026-08-05T00:45:18.770532+00:00"}