{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XRXESRULOKATW7KFSUUF36GC4G","short_pith_number":"pith:XRXESRUL","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"},"canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","source":{"kind":"arxiv","id":"2503.19755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19755","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19755v1","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19755","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"XRXESRULOKAT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XRXESRULOKATW7KF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XRXESRUL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XRXESRULOKATW7KFSUUF36GC4G","target":"record","payload":{"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"},"canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","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"},"source_kind":"arxiv","source_id":"2503.19755","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sgn+13aC8u2ectBOqE4VrjAEQ6iSDLUi5yaJk8BZB3uEsptzMtyxP1AwMHmm3r6K8IR79C+tP4tnbkWQK8R1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:42:04.400304Z"},"content_sha256":"60e276daf172828f7cfdf8ecdd771501cd0e23652120d809ffd94f18727ea3dc","schema_version":"1.0","event_id":"sha256:60e276daf172828f7cfdf8ecdd771501cd0e23652120d809ffd94f18727ea3dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XRXESRULOKATW7KFSUUF36GC4G","target":"graph","payload":{"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"},"verdict_id":"fc19b1ec-7fcb-4ffd-8c9c-fe7ab1c55490"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLFAwRvVyCx1HPUOijjj9OSxMyNED3dAWg1IcXfXgwBOuND7Orcg59YMGdXEOFHJv7V/sWCyTRqFIdocdLg3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:42:04.401266Z"},"content_sha256":"1ff031eb44e14a1700501aaaadeb9d2bfa3dc2a4922b8b9e0a96650aaa3e036c","schema_version":"1.0","event_id":"sha256:1ff031eb44e14a1700501aaaadeb9d2bfa3dc2a4922b8b9e0a96650aaa3e036c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/bundle.json","state_url":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRXESRULOKATW7KFSUUF36GC4G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T21:42:04Z","links":{"resolver":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G","bundle":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/bundle.json","state":"https://pith.science/pith/XRXESRULOKATW7KFSUUF36GC4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRXESRULOKATW7KFSUUF36GC4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XRXESRULOKATW7KFSUUF36GC4G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38a146fe1ac8e4d8e2ac496a60f59528ffd182e3e736ae2ef51f1774e8cd4f91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T15:18:43Z","title_canon_sha256":"e6b883d4f076b60131e6a6bb77665fdb875b0feae3729b26a76fe1e1b585b8dd"},"schema_version":"1.0","source":{"id":"2503.19755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19755","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19755v1","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19755","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"XRXESRULOKAT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XRXESRULOKATW7KF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XRXESRUL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1ff031eb44e14a1700501aaaadeb9d2bfa3dc2a4922b8b9e0a96650aaa3e036c","target":"graph","created_at":"2026-05-17T23:38:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."}],"snapshot_sha256":"b3c5ebaddc4da911d6e8ff99255b4994d061f624e73615cd55b80fa9f31f4af6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f7b1533bd7b23ee76bf376a8176ba65f5bcde82785c89854bebb18d564e2224e"},"paper":{"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","authors_text":"Bing Wang, Chong Zhang, Diankun Zhang, Dingkang Liang, Dingyuan Zhang, Haoyu Fu, Hongwei Xie, Jianfeng Cui, Xiang Bai, Zongchuang Zhao","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T15:18:43Z","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"},"references":{"count":103,"internal_anchors":13,"resolved_work":103,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Flamingo: a visual language model for few-shot learning","work_id":"cc3738fb-da60-4a20-8b03-c795998bbe7a","year":2022},{"cited_arxiv_id":"2312.11805","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023},{"cited_arxiv_id":"2308.12966","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Improving image generation with better captions","work_id":"31ac6ff5-6cb8-46dd-bbd4-7e8c4804cc01","year":2023}],"snapshot_sha256":"568a0696150bb0ca2a4b00373b29c66f3f65f5bd367278f565fb0ecbe9a5cb58"},"source":{"id":"2503.19755","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T08:04:53.553705Z","id":"fc19b1ec-7fcb-4ffd-8c9c-fe7ab1c55490","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"","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.","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."}},"verdict_id":"fc19b1ec-7fcb-4ffd-8c9c-fe7ab1c55490"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:60e276daf172828f7cfdf8ecdd771501cd0e23652120d809ffd94f18727ea3dc","target":"record","created_at":"2026-05-17T23:38:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"38a146fe1ac8e4d8e2ac496a60f59528ffd182e3e736ae2ef51f1774e8cd4f91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T15:18:43Z","title_canon_sha256":"e6b883d4f076b60131e6a6bb77665fdb875b0feae3729b26a76fe1e1b585b8dd"},"schema_version":"1.0","source":{"id":"2503.19755","kind":"arxiv","version":1}},"canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc6e49468b72813b7d4595285df8c2e1b90a7d8aabb0b50e716e5b121db8db68","first_computed_at":"2026-05-17T23:38:14.609345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.609345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4IQcxeNsXGiEiESDZbJA7ezc3Ri1K6shVwv8GGICCSpYBozwetCtdUmvvQ7UyO2kPVC+wIIKx5D1IivXB2VxBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.610107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60e276daf172828f7cfdf8ecdd771501cd0e23652120d809ffd94f18727ea3dc","sha256:1ff031eb44e14a1700501aaaadeb9d2bfa3dc2a4922b8b9e0a96650aaa3e036c"],"state_sha256":"9a81e23e30273c612629313ba2bd2738dc9a34c32f5e7d70052bbc32e30d32b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZ5GTVi2qwnFbBSvYOqkMpnNhrr62K60/dCHQTsrOmkO7SxBMH5uFAO4YnIi1dOqSw7kTP6k5vZ+InNAl44MCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:42:04.405513Z","bundle_sha256":"aa716bef4f5ffbf2631aca5f2899e88fe5cbe6003839cdbdf57f0ae8c82c47fa"}}