{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6TOKWQ4TQZOTIDHRTSQLJYNFKQ","short_pith_number":"pith:6TOKWQ4T","schema_version":"1.0","canonical_sha256":"f4dcab4393865d340cf19ca0b4e1a5542a72e68d8d899583a4f76afb9d3dcba6","source":{"kind":"arxiv","id":"2508.12603","version":1},"attestation_state":"computed","paper":{"title":"ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Cui, Jiaru Zhang, Juntong Peng, Prashanth Sankaranarayanan, Ruqi Zhang, Sung-Yeon Park, Yupeng Zhou, Zichong Yang, Ziran Wang","submitted_at":"2025-08-18T04:01:56Z","abstract_excerpt":"End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential, token-by-token generation process of these models results in high inference latency and cannot perform bidirectional reasoning, making them unsuitable for dynamic, safety-critical environments. To overcome these challenges, we introduce ViLaD, a novel Large Vision Language Diffusion (LVLD) framework for end-to-end autonomous driving that represents a paradigm shift"},"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":"2508.12603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T04:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"cd69baf83cacb701fb089cac6a66283be174d69ae1a120d819dae9a8e0a13eca","abstract_canon_sha256":"30638ee5c8231f9a510ee629fd0a8c564c9c16ab142372b23327d43bd7b0e8de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:23.832203Z","signature_b64":"VP0cuPF9etlrpdUThaX4YANHCo61rLUJZpe9/M4RrWyzrVLcfHfBKkHT0x0D6kLIo0/waV6tVtCGIqDdO2uTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4dcab4393865d340cf19ca0b4e1a5542a72e68d8d899583a4f76afb9d3dcba6","last_reissued_at":"2026-07-05T11:55:23.831826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:23.831826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Cui, Jiaru Zhang, Juntong Peng, Prashanth Sankaranarayanan, Ruqi Zhang, Sung-Yeon Park, Yupeng Zhou, Zichong Yang, Ziran Wang","submitted_at":"2025-08-18T04:01:56Z","abstract_excerpt":"End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential, token-by-token generation process of these models results in high inference latency and cannot perform bidirectional reasoning, making them unsuitable for dynamic, safety-critical environments. To overcome these challenges, we introduce ViLaD, a novel Large Vision Language Diffusion (LVLD) framework for end-to-end autonomous driving that represents a paradigm shift"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12603","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/2508.12603/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":"2508.12603","created_at":"2026-07-05T11:55:23.831886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12603v1","created_at":"2026-07-05T11:55:23.831886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12603","created_at":"2026-07-05T11:55:23.831886+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TOKWQ4TQZOT","created_at":"2026-07-05T11:55:23.831886+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TOKWQ4TQZOTIDHR","created_at":"2026-07-05T11:55:23.831886+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TOKWQ4T","created_at":"2026-07-05T11:55:23.831886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21165","citing_title":"OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ","json":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ.json","graph_json":"https://pith.science/api/pith-number/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/graph.json","events_json":"https://pith.science/api/pith-number/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/events.json","paper":"https://pith.science/paper/6TOKWQ4T"},"agent_actions":{"view_html":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ","download_json":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ.json","view_paper":"https://pith.science/paper/6TOKWQ4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12603&json=true","fetch_graph":"https://pith.science/api/pith-number/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/action/storage_attestation","attest_author":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/action/author_attestation","sign_citation":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/action/citation_signature","submit_replication":"https://pith.science/pith/6TOKWQ4TQZOTIDHRTSQLJYNFKQ/action/replication_record"}},"created_at":"2026-07-05T11:55:23.831886+00:00","updated_at":"2026-07-05T11:55:23.831886+00:00"}