{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4EC3NXFQNJ5TWNW7FQD45UTED","short_pith_number":"pith:D4EC3NXF","schema_version":"1.0","canonical_sha256":"1f082db6e58353d9d9b6f9603e769320fa12d8e5a9a04020f7cec95163fa31ab","source":{"kind":"arxiv","id":"2404.06892","version":1},"attestation_state":"computed","paper":{"title":"SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Chi Zhang, Diankun Zhang, Feiyang Tan, Guoan Wang, Hangning Zhou, Haotian Yao, Jiahao Gong, Jianbo Zhao, Ningzi Wang, Qibin Zhou, Runwen Zhu, Siyu Zhang, Wenyuan Zhang, Xiaoguang Di, Xiaojun Liu, Xiwu Chen, Ziyao Xu","submitted_at":"2024-04-10T10:34:34Z","abstract_excerpt":"End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any d"},"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":"2404.06892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T10:34:34Z","cross_cats_sorted":[],"title_canon_sha256":"1dc704a60bba3efba075be1f39a205bacf221b26354d837ce91a920005bdd05c","abstract_canon_sha256":"53d14779eb98d4437c6f22cd03b02ea68a59a4c84a3b82ab78c567a98c69f7bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:31.893970Z","signature_b64":"2Z7k+Zfaymr3YqWSvkpXad8MPHgos4xUQMZM1F82gGbcTuPxBcEBceXYP/wQTUzTR58kD4vL4RoaWb9VEn1wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f082db6e58353d9d9b6f9603e769320fa12d8e5a9a04020f7cec95163fa31ab","last_reissued_at":"2026-07-05T08:06:31.893518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:31.893518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Chi Zhang, Diankun Zhang, Feiyang Tan, Guoan Wang, Hangning Zhou, Haotian Yao, Jiahao Gong, Jianbo Zhao, Ningzi Wang, Qibin Zhou, Runwen Zhu, Siyu Zhang, Wenyuan Zhang, Xiaoguang Di, Xiaojun Liu, Xiwu Chen, Ziyao Xu","submitted_at":"2024-04-10T10:34:34Z","abstract_excerpt":"End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06892","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/2404.06892/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":"2404.06892","created_at":"2026-07-05T08:06:31.893582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06892v1","created_at":"2026-07-05T08:06:31.893582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06892","created_at":"2026-07-05T08:06:31.893582+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4EC3NXFQNJ5","created_at":"2026-07-05T08:06:31.893582+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4EC3NXFQNJ5TWNW","created_at":"2026-07-05T08:06:31.893582+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4EC3NXF","created_at":"2026-07-05T08:06:31.893582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.09887","citing_title":"Planning by Simulation: Motion Planning with Learning-based Parallel Scenario Prediction for Autonomous Driving","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19755","citing_title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05449","citing_title":"Not All Agents Matter: From Global Attention Dilution to Risk-Prioritized Game Planning","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED","json":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED.json","graph_json":"https://pith.science/api/pith-number/D4EC3NXFQNJ5TWNW7FQD45UTED/graph.json","events_json":"https://pith.science/api/pith-number/D4EC3NXFQNJ5TWNW7FQD45UTED/events.json","paper":"https://pith.science/paper/D4EC3NXF"},"agent_actions":{"view_html":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED","download_json":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED.json","view_paper":"https://pith.science/paper/D4EC3NXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06892&json=true","fetch_graph":"https://pith.science/api/pith-number/D4EC3NXFQNJ5TWNW7FQD45UTED/graph.json","fetch_events":"https://pith.science/api/pith-number/D4EC3NXFQNJ5TWNW7FQD45UTED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED/action/storage_attestation","attest_author":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED/action/author_attestation","sign_citation":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED/action/citation_signature","submit_replication":"https://pith.science/pith/D4EC3NXFQNJ5TWNW7FQD45UTED/action/replication_record"}},"created_at":"2026-07-05T08:06:31.893582+00:00","updated_at":"2026-07-05T08:06:31.893582+00:00"}