{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XRXESRULOKATW7KFSUUF36GC4G","short_pith_number":"pith:XRXESRUL","schema_version":"1.0","canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","source":{"kind":"arxiv","id":"2503.19755","version":1},"attestation_state":"computed","paper":{"title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ORION reports 77.74 Driving Score and 54.62% Success Rate on Bench2Drive, outperforming prior end-to-end methods by 14.28 DS and 19.61% SR through unified VQA and planning optimization.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Chong Zhang, Diankun Zhang, Dingkang Liang, Dingyuan Zhang, Haoyu Fu, Hongwei Xie, Jianfeng Cui, Xiang Bai, Zongchuang Zhao","submitted_at":"2025-03-25T15:18:43Z","abstract_excerpt":"End-to-end (E2E) autonomous driving methods still struggle to make correct decisions in interactive closed-loop evaluation due to limited causal reasoning capability. Current methods attempt to leverage the powerful understanding and reasoning abilities of Vision-Language Models (VLMs) to resolve this dilemma. However, the problem is still open that few VLMs for E2E methods perform well in the closed-loop evaluation due to the gap between the semantic reasoning space and the purely numerical trajectory output in the action space. To tackle this issue, we propose ORION, a holistic E2E autonomou"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2503.19755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T15:18:43Z","cross_cats_sorted":[],"title_canon_sha256":"e6b883d4f076b60131e6a6bb77665fdb875b0feae3729b26a76fe1e1b585b8dd","abstract_canon_sha256":"38a146fe1ac8e4d8e2ac496a60f59528ffd182e3e736ae2ef51f1774e8cd4f91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.610107Z","signature_b64":"4IQcxeNsXGiEiESDZbJA7ezc3Ri1K6shVwv8GGICCSpYBozwetCtdUmvvQ7UyO2kPVC+wIIKx5D1IivXB2VxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","last_reissued_at":"2026-05-17T23:38:14.609345Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.609345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ORION reports 77.74 Driving Score and 54.62% Success Rate on Bench2Drive, outperforming prior end-to-end methods by 14.28 DS and 19.61% SR through unified VQA and planning optimization.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Chong Zhang, Diankun Zhang, Dingkang Liang, Dingyuan Zhang, Haoyu Fu, Hongwei Xie, Jianfeng Cui, Xiang Bai, Zongchuang Zhao","submitted_at":"2025-03-25T15:18:43Z","abstract_excerpt":"End-to-end (E2E) autonomous driving methods still struggle to make correct decisions in interactive closed-loop evaluation due to limited causal reasoning capability. Current methods attempt to leverage the powerful understanding and reasoning abilities of Vision-Language Models (VLMs) to resolve this dilemma. However, the problem is still open that few VLMs for E2E methods perform well in the closed-loop evaluation due to the gap between the semantic reasoning space and the purely numerical trajectory output in the action space. To tackle this issue, we propose ORION, a holistic E2E autonomou"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Our method achieves an impressive closed-loop performance of 77.74 Driving Score (DS) and 54.62% Success Rate (SR) on the challenge Bench2Drive datasets, which outperforms state-of-the-art (SOTA) methods by a large margin of 14.28 DS and 19.61% SR.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that aligning the reasoning space of the LLM with the numerical action space through unified E2E optimization will reliably improve closed-loop causal reasoning and trajectory quality without introducing new failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ORION reports 77.74 Driving Score and 54.62% Success Rate on Bench2Drive, outperforming prior end-to-end methods by 14.28 DS and 19.61% SR through unified VQA and planning optimization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"b3c5ebaddc4da911d6e8ff99255b4994d061f624e73615cd55b80fa9f31f4af6"},"source":{"id":"2503.19755","kind":"arxiv","version":1},"verdict":{"id":"fc19b1ec-7fcb-4ffd-8c9c-fe7ab1c55490","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T08:04:53.553705Z","strongest_claim":"Our method achieves an impressive closed-loop performance of 77.74 Driving Score (DS) and 54.62% Success Rate (SR) on the challenge Bench2Drive datasets, which outperforms state-of-the-art (SOTA) methods by a large margin of 14.28 DS and 19.61% SR.","one_line_summary":"ORION reports 77.74 Driving Score and 54.62% Success Rate on Bench2Drive, outperforming prior end-to-end methods by 14.28 DS and 19.61% SR through unified VQA and planning optimization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that aligning the reasoning space of the LLM with the numerical action space through unified E2E optimization will reliably improve closed-loop causal reasoning and trajectory quality without introducing new failure modes.","pith_extraction_headline":""},"references":{"count":103,"sample":[{"doi":"","year":null,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"cc3738fb-da60-4a20-8b03-c795998bbe7a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","ref_index":3,"cited_arxiv_id":"2312.11805","is_internal_anchor":true},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":4,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2023,"title":"Improving image generation with better captions","work_id":"31ac6ff5-6cb8-46dd-bbd4-7e8c4804cc01","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":103,"snapshot_sha256":"568a0696150bb0ca2a4b00373b29c66f3f65f5bd367278f565fb0ecbe9a5cb58","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f7b1533bd7b23ee76bf376a8176ba65f5bcde82785c89854bebb18d564e2224e"},"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":"2503.19755","created_at":"2026-05-17T23:38:14.609470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19755v1","created_at":"2026-05-17T23:38:14.609470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19755","created_at":"2026-05-17T23:38:14.609470+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRXESRULOKAT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRXESRULOKATW7KF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRXESRUL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":22,"sample":[{"citing_arxiv_id":"2512.10719","citing_title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14201","citing_title":"MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2509.00789","citing_title":"CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12796","citing_title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10226","citing_title":"Latent Chain-of-Thought World Modeling for End-to-End Driving","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09465","citing_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14201","citing_title":"MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving","ref_index":9,"is_internal_anchor":true},{"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":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08133","citing_title":"VLADriver-RAG: Retrieval-Augmented Vision-Language-Action Models for Autonomous Driving","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08133","citing_title":"VLADriver-RAG: Retrieval-Augmented Vision-Language-Action Models for Autonomous Driving","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08975","citing_title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10386","citing_title":"GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19710","citing_title":"SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17915","citing_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08266","citing_title":"Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08535","citing_title":"Fail2Drive: Benchmarking Closed-Loop Driving Generalization","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02762","citing_title":"Unified Map Prior Encoder for Mapping and Planning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G","json":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G.json","graph_json":"https://pith.science/api/pith-number/XRXESRULOKATW7KFSUUF36GC4G/graph.json","events_json":"https://pith.science/api/pith-number/XRXESRULOKATW7KFSUUF36GC4G/events.json","paper":"https://pith.science/paper/XRXESRUL"},"agent_actions":{"view_html":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G","download_json":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G.json","view_paper":"https://pith.science/paper/XRXESRUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19755&json=true","fetch_graph":"https://pith.science/api/pith-number/XRXESRULOKATW7KFSUUF36GC4G/graph.json","fetch_events":"https://pith.science/api/pith-number/XRXESRULOKATW7KFSUUF36GC4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/action/storage_attestation","attest_author":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/action/author_attestation","sign_citation":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/action/citation_signature","submit_replication":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/action/replication_record"}},"created_at":"2026-05-17T23:38:14.609470+00:00","updated_at":"2026-05-17T23:38:14.609470+00:00"}