{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F6JYQNSIM2QOS5F2UOWBCZ57OM","short_pith_number":"pith:F6JYQNSI","schema_version":"1.0","canonical_sha256":"2f9388364866a0e974baa3ac1167bf7328bef2e4b0e71f3d2b970cc1d3a0378e","source":{"kind":"arxiv","id":"2303.12077","version":3},"attestation_state":"computed","paper":{"title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bencheng Liao, Bo Jiang, Chang Huang, Helong Zhou, Jiajie Chen, Qian Zhang, Qing Xu, Shaoyu Chen, Wenyu Liu, Xinggang Wang","submitted_at":"2023-03-21T17:59:22Z","abstract_excerpt":"Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic map) to perform planning, which is computationally intensive and misses the instance-level structure information. In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation. The proposed vectorized paradigm has two significant advantages. On one hand, VAD exploits the vectorized ag"},"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":"2303.12077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-21T17:59:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a793c2994f9dc866b9e82c41a380fbb5d2cf73ede486cc7e365c72f2ae3025d7","abstract_canon_sha256":"ac929e571e36c8a5557fb559cbbeb9f7ff15b80855e8e88e67b0ffe4bccba78b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:06.806101Z","signature_b64":"CSSb4We3/C7eT4CCNbW7NHoFDbTw64XDfLALTqjcKws9hs9qzBq10ugV+JYnJbIYs+SWVblYjS7zjHvtyLK3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9388364866a0e974baa3ac1167bf7328bef2e4b0e71f3d2b970cc1d3a0378e","last_reissued_at":"2026-07-05T06:44:06.805543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:06.805543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bencheng Liao, Bo Jiang, Chang Huang, Helong Zhou, Jiajie Chen, Qian Zhang, Qing Xu, Shaoyu Chen, Wenyu Liu, Xinggang Wang","submitted_at":"2023-03-21T17:59:22Z","abstract_excerpt":"Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic map) to perform planning, which is computationally intensive and misses the instance-level structure information. In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation. The proposed vectorized paradigm has two significant advantages. On one hand, VAD exploits the vectorized ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12077","kind":"arxiv","version":3},"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/2303.12077/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":"2303.12077","created_at":"2026-07-05T06:44:06.805608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12077v3","created_at":"2026-07-05T06:44:06.805608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12077","created_at":"2026-07-05T06:44:06.805608+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6JYQNSIM2QO","created_at":"2026-07-05T06:44:06.805608+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6JYQNSIM2QOS5F2","created_at":"2026-07-05T06:44:06.805608+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6JYQNSI","created_at":"2026-07-05T06:44:06.805608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.10430","citing_title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01415","citing_title":"GPT-Driver: Learning to Drive with GPT","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2402.12289","citing_title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08975","citing_title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04355","citing_title":"InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM","json":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM.json","graph_json":"https://pith.science/api/pith-number/F6JYQNSIM2QOS5F2UOWBCZ57OM/graph.json","events_json":"https://pith.science/api/pith-number/F6JYQNSIM2QOS5F2UOWBCZ57OM/events.json","paper":"https://pith.science/paper/F6JYQNSI"},"agent_actions":{"view_html":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM","download_json":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM.json","view_paper":"https://pith.science/paper/F6JYQNSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12077&json=true","fetch_graph":"https://pith.science/api/pith-number/F6JYQNSIM2QOS5F2UOWBCZ57OM/graph.json","fetch_events":"https://pith.science/api/pith-number/F6JYQNSIM2QOS5F2UOWBCZ57OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM/action/storage_attestation","attest_author":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM/action/author_attestation","sign_citation":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM/action/citation_signature","submit_replication":"https://pith.science/pith/F6JYQNSIM2QOS5F2UOWBCZ57OM/action/replication_record"}},"created_at":"2026-07-05T06:44:06.805608+00:00","updated_at":"2026-07-05T06:44:06.805608+00:00"}