{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L4IGSFN2OSXOH3NRLB7AOU35XE","short_pith_number":"pith:L4IGSFN2","schema_version":"1.0","canonical_sha256":"5f106915ba74aee3edb1587e07537db911c7f470dd8f82d6be0c0a6bb5a04f75","source":{"kind":"arxiv","id":"2503.07656","version":2},"attestation_state":"computed","paper":{"title":"DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Junchi Yan, Junqi You, Xiaosong Jia, Zhiyuan Zhang","submitted_at":"2025-03-07T11:41:18Z","abstract_excerpt":"End-to-end autonomous driving (E2E-AD) has emerged as a trend in the field of autonomous driving, promising a data-driven, scalable approach to system design. However, existing E2E-AD methods usually adopt the sequential paradigm of perception-prediction-planning, which leads to cumulative errors and training instability. The manual ordering of tasks also limits the system`s ability to leverage synergies between tasks (for example, planning-aware perception and game-theoretic interactive prediction and planning). Moreover, the dense BEV representation adopted by existing methods brings computa"},"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":"2503.07656","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T11:41:18Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"b2b58c1c3a06c123a9ede5f52abc962c8d447bdf57fdb439e96e52870a8b0834","abstract_canon_sha256":"5d8e8fa548060840436416b5cdfa2f21f335f3ac64b3ea20b572d172ca87d481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:33.782888Z","signature_b64":"mEonNazs5Tcl6pxWREnOVj12wrzFaOhN+nO2pcQHgOJeSmBt/3utK1JUNk97dZF2BEdNUh07ItVyfsMm006wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f106915ba74aee3edb1587e07537db911c7f470dd8f82d6be0c0a6bb5a04f75","last_reissued_at":"2026-07-05T11:35:33.782453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:33.782453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Junchi Yan, Junqi You, Xiaosong Jia, Zhiyuan Zhang","submitted_at":"2025-03-07T11:41:18Z","abstract_excerpt":"End-to-end autonomous driving (E2E-AD) has emerged as a trend in the field of autonomous driving, promising a data-driven, scalable approach to system design. However, existing E2E-AD methods usually adopt the sequential paradigm of perception-prediction-planning, which leads to cumulative errors and training instability. The manual ordering of tasks also limits the system`s ability to leverage synergies between tasks (for example, planning-aware perception and game-theoretic interactive prediction and planning). Moreover, the dense BEV representation adopted by existing methods brings computa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07656","kind":"arxiv","version":2},"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/2503.07656/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":"2503.07656","created_at":"2026-07-05T11:35:33.782506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07656v2","created_at":"2026-07-05T11:35:33.782506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07656","created_at":"2026-07-05T11:35:33.782506+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4IGSFN2OSXO","created_at":"2026-07-05T11:35:33.782506+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4IGSFN2OSXOH3NR","created_at":"2026-07-05T11:35:33.782506+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4IGSFN2","created_at":"2026-07-05T11:35:33.782506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25736","citing_title":"UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12396","citing_title":"VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17284","citing_title":"CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous Driving","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04049","citing_title":"DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01762","citing_title":"AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18757","citing_title":"Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08975","citing_title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00066","citing_title":"Do Open-Loop Metrics Predict Closed-Loop Driving? A Cross-Benchmark Correlation Study of NAVSIM and Bench2Drive","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17915","citing_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12208","citing_title":"Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08266","citing_title":"Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08719","citing_title":"LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE","json":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE.json","graph_json":"https://pith.science/api/pith-number/L4IGSFN2OSXOH3NRLB7AOU35XE/graph.json","events_json":"https://pith.science/api/pith-number/L4IGSFN2OSXOH3NRLB7AOU35XE/events.json","paper":"https://pith.science/paper/L4IGSFN2"},"agent_actions":{"view_html":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE","download_json":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE.json","view_paper":"https://pith.science/paper/L4IGSFN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07656&json=true","fetch_graph":"https://pith.science/api/pith-number/L4IGSFN2OSXOH3NRLB7AOU35XE/graph.json","fetch_events":"https://pith.science/api/pith-number/L4IGSFN2OSXOH3NRLB7AOU35XE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE/action/storage_attestation","attest_author":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE/action/author_attestation","sign_citation":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE/action/citation_signature","submit_replication":"https://pith.science/pith/L4IGSFN2OSXOH3NRLB7AOU35XE/action/replication_record"}},"created_at":"2026-07-05T11:35:33.782506+00:00","updated_at":"2026-07-05T11:35:33.782506+00:00"}