{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O3X74XGDYRARI2DVKCRZFUGOYK","short_pith_number":"pith:O3X74XGD","schema_version":"1.0","canonical_sha256":"76effe5cc3c44114687550a392d0cec28181c4ff98a0743f01241e6653d2c300","source":{"kind":"arxiv","id":"2403.16996","version":1},"attestation_state":"computed","paper":{"title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Ping Luo, Ruihang Chu, Tianqi Wang, Zhenguo Li","submitted_at":"2024-03-25T17:59:01Z","abstract_excerpt":"End-to-end driving has made significant progress in recent years, demonstrating benefits such as system simplicity and competitive driving performance under both open-loop and closed-loop settings. Nevertheless, the lack of interpretability and controllability in its driving decisions hinders real-world deployment for end-to-end driving systems. In this paper, we collect a comprehensive end-to-end driving dataset named DriveCoT, leveraging the CARLA simulator. It contains sensor data, control decisions, and chain-of-thought labels to indicate the reasoning process. We utilize the challenging 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":"2403.16996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:01Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a412696157d95b3f1694eda7d4f0c4618e7fb4c768b63618200e9dbbd1f2958d","abstract_canon_sha256":"6c327db8038dabd93c1b0dd90f9421fd5a005ef3d5ba7b254bb4dcd80303c774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:23.568011Z","signature_b64":"i/UewMSD46JBRtFEV5aaN112yjTYj0odWIwq5fHCeP4KTJ9aItJOf3SObd6h3i1ROA0mnvH0wjpQHWCbCnXoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76effe5cc3c44114687550a392d0cec28181c4ff98a0743f01241e6653d2c300","last_reissued_at":"2026-07-05T08:00:23.567539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:23.567539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Ping Luo, Ruihang Chu, Tianqi Wang, Zhenguo Li","submitted_at":"2024-03-25T17:59:01Z","abstract_excerpt":"End-to-end driving has made significant progress in recent years, demonstrating benefits such as system simplicity and competitive driving performance under both open-loop and closed-loop settings. Nevertheless, the lack of interpretability and controllability in its driving decisions hinders real-world deployment for end-to-end driving systems. In this paper, we collect a comprehensive end-to-end driving dataset named DriveCoT, leveraging the CARLA simulator. It contains sensor data, control decisions, and chain-of-thought labels to indicate the reasoning process. We utilize the challenging d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16996","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/2403.16996/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":"2403.16996","created_at":"2026-07-05T08:00:23.567597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16996v1","created_at":"2026-07-05T08:00:23.567597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16996","created_at":"2026-07-05T08:00:23.567597+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3X74XGDYRAR","created_at":"2026-07-05T08:00:23.567597+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3X74XGDYRARI2DV","created_at":"2026-07-05T08:00:23.567597+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3X74XGD","created_at":"2026-07-05T08:00:23.567597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23938","citing_title":"Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21165","citing_title":"OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20641","citing_title":"MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23163","citing_title":"Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23163","citing_title":"Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00088","citing_title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10226","citing_title":"Latent Chain-of-Thought World Modeling for End-to-End Driving","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23262","citing_title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17024","citing_title":"CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK","json":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK.json","graph_json":"https://pith.science/api/pith-number/O3X74XGDYRARI2DVKCRZFUGOYK/graph.json","events_json":"https://pith.science/api/pith-number/O3X74XGDYRARI2DVKCRZFUGOYK/events.json","paper":"https://pith.science/paper/O3X74XGD"},"agent_actions":{"view_html":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK","download_json":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK.json","view_paper":"https://pith.science/paper/O3X74XGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16996&json=true","fetch_graph":"https://pith.science/api/pith-number/O3X74XGDYRARI2DVKCRZFUGOYK/graph.json","fetch_events":"https://pith.science/api/pith-number/O3X74XGDYRARI2DVKCRZFUGOYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK/action/storage_attestation","attest_author":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK/action/author_attestation","sign_citation":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK/action/citation_signature","submit_replication":"https://pith.science/pith/O3X74XGDYRARI2DVKCRZFUGOYK/action/replication_record"}},"created_at":"2026-07-05T08:00:23.567597+00:00","updated_at":"2026-07-05T08:00:23.567597+00:00"}