{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AKLOOSBJVAHH4UUP3J3MB543UM","short_pith_number":"pith:AKLOOSBJ","canonical_record":{"source":{"id":"2310.01415","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:59:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"bd8b88211642ffee7a5b88d0a713aeba0091526cf84ee70b61015af5407a6e96","abstract_canon_sha256":"40efd13105f5f13dc523cb36e44e23762eadac92986e69c1b3f54d0df8f43431"},"schema_version":"1.0"},"canonical_sha256":"0296e74829a80e7e528fda76c0f79ba30073cd162829e8088e6a43cbe42a3405","source":{"kind":"arxiv","id":"2310.01415","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01415","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01415v3","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01415","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"AKLOOSBJVAHH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"AKLOOSBJVAHH4UUP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"AKLOOSBJ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AKLOOSBJVAHH4UUP3J3MB543UM","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01415","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:59:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"bd8b88211642ffee7a5b88d0a713aeba0091526cf84ee70b61015af5407a6e96","abstract_canon_sha256":"40efd13105f5f13dc523cb36e44e23762eadac92986e69c1b3f54d0df8f43431"},"schema_version":"1.0"},"canonical_sha256":"0296e74829a80e7e528fda76c0f79ba30073cd162829e8088e6a43cbe42a3405","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.291477Z","signature_b64":"P0qjl+Y5QSXeNVV4Ihghgk4QDyZdkNxx0uUHlbThl8rF0/xCoV1U/HLEQiRFrFsuVQu8gddkqgg8NCs+D644DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0296e74829a80e7e528fda76c0f79ba30073cd162829e8088e6a43cbe42a3405","last_reissued_at":"2026-05-17T23:38:52.291019Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.291019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01415","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lg1wWVT4TzeEcSX1tYxNO4RG3lhivYA9Y7p4839V65P/uEJDbOOh9saEcIcDIWQyj23BFbncGm30GTf61B4MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:35:52.670959Z"},"content_sha256":"e39da5beaad828290efb57369564f6a3d0a61ae007f6f1cc66466f7ff2371450","schema_version":"1.0","event_id":"sha256:e39da5beaad828290efb57369564f6a3d0a61ae007f6f1cc66466f7ff2371450"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AKLOOSBJVAHH4UUP3J3MB543UM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPT-Driver: Learning to Drive with GPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions.","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hang Zhao, Jiageng Mao, Junjie Ye, Yue Wang, YuXi Qian","submitted_at":"2023-10-02T17:59:57Z","abstract_excerpt":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles... the fundamental insight of our approach is the reformulation of motion planning as a language modeling problem.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an LLM prompted and fine-tuned on language descriptions of coordinates will produce numerically precise, collision-free trajectories in safety-critical, out-of-distribution driving scenes without systematic hallucination or unsafe outputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c5c21b6a8a6c096ea29a4f9f87614aff856f05fc2f4e17a4a2b61740a5858944"},"source":{"id":"2310.01415","kind":"arxiv","version":3},"verdict":{"id":"ab952ed4-b768-45fc-b23c-0f647c5eb678","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:59:41.179135Z","strongest_claim":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles... the fundamental insight of our approach is the reformulation of motion planning as a language modeling problem.","one_line_summary":"GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an LLM prompted and fine-tuned on language descriptions of coordinates will produce numerically precise, collision-free trajectories in safety-critical, out-of-distribution driving scenes without systematic hallucination or unsafe outputs.","pith_extraction_headline":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions."},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":null,"title":"End to End Learning for Self-Driving Cars","work_id":"3184be8a-a518-4a34-9adf-d8f3bb396533","ref_index":2,"cited_arxiv_id":"1604.07316","is_internal_anchor":true},{"doi":"","year":null,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","ref_index":3,"cited_arxiv_id":"2307.15818","is_internal_anchor":true},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"f93ff324-f230-4a46-97b9-6b103c35585d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Cheng, B., Girshick, R., Dollar, P., Berg, A","work_id":"c10c912e-59c0-4cd0-b849-c2274cb7a92e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"212a500f717d88364bec4f7649b947f58511308103bde5a06d6bcd1aea9f6b68","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b8e81b69e9b2dc151969f520eb403b3cf15d9916ae8c218bf2f1e891b9cfea5"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ab952ed4-b768-45fc-b23c-0f647c5eb678"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKqXTPJraExCLDOvHrsV4LSRKU2vuorDXJqCvcEHqpLd0XYa7Npb562ilmb+5uIe6K/m9FGdUQ1M19huWvWkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:35:52.671988Z"},"content_sha256":"ed10b572462c669636c344753c667b146592a479a531cdc2b06c2edf77284128","schema_version":"1.0","event_id":"sha256:ed10b572462c669636c344753c667b146592a479a531cdc2b06c2edf77284128"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKLOOSBJVAHH4UUP3J3MB543UM/bundle.json","state_url":"https://pith.science/pith/AKLOOSBJVAHH4UUP3J3MB543UM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKLOOSBJVAHH4UUP3J3MB543UM/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":"2026-06-10T06:35:52Z","links":{"resolver":"https://pith.science/pith/AKLOOSBJVAHH4UUP3J3MB543UM","bundle":"https://pith.science/pith/AKLOOSBJVAHH4UUP3J3MB543UM/bundle.json","state":"https://pith.science/pith/AKLOOSBJVAHH4UUP3J3MB543UM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKLOOSBJVAHH4UUP3J3MB543UM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AKLOOSBJVAHH4UUP3J3MB543UM","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":"40efd13105f5f13dc523cb36e44e23762eadac92986e69c1b3f54d0df8f43431","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:59:57Z","title_canon_sha256":"bd8b88211642ffee7a5b88d0a713aeba0091526cf84ee70b61015af5407a6e96"},"schema_version":"1.0","source":{"id":"2310.01415","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01415","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01415v3","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01415","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"AKLOOSBJVAHH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"AKLOOSBJVAHH4UUP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"AKLOOSBJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:ed10b572462c669636c344753c667b146592a479a531cdc2b06c2edf77284128","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles... the fundamental insight of our approach is the reformulation of motion planning as a language modeling problem."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That an LLM prompted and fine-tuned on language descriptions of coordinates will produce numerically precise, collision-free trajectories in safety-critical, out-of-distribution driving scenes without systematic hallucination or unsafe outputs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions."}],"snapshot_sha256":"c5c21b6a8a6c096ea29a4f9f87614aff856f05fc2f4e17a4a2b61740a5858944"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b8e81b69e9b2dc151969f520eb403b3cf15d9916ae8c218bf2f1e891b9cfea5"},"paper":{"abstract_excerpt":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capa","authors_text":"Hang Zhao, Jiageng Mao, Junjie Ye, Yue Wang, YuXi Qian","cross_cats":["cs.AI","cs.CL","cs.RO"],"headline":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:59:57Z","title":"GPT-Driver: Learning to Drive with GPT"},"references":{"count":17,"internal_anchors":7,"resolved_work":17,"sample":[{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":null},{"cited_arxiv_id":"1604.07316","doi":"","is_internal_anchor":true,"ref_index":2,"title":"End to End Learning for Self-Driving Cars","work_id":"3184be8a-a518-4a34-9adf-d8f3bb396533","year":null},{"cited_arxiv_id":"2307.15818","doi":"","is_internal_anchor":true,"ref_index":3,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Language models are few-shot learners","work_id":"f93ff324-f230-4a46-97b9-6b103c35585d","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Cheng, B., Girshick, R., Dollar, P., Berg, A","work_id":"c10c912e-59c0-4cd0-b849-c2274cb7a92e","year":null}],"snapshot_sha256":"212a500f717d88364bec4f7649b947f58511308103bde5a06d6bcd1aea9f6b68"},"source":{"id":"2310.01415","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T14:59:41.179135Z","id":"ab952ed4-b768-45fc-b23c-0f647c5eb678","model_set":{"reader":"grok-4.3"},"one_line_summary":"GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Reformulating motion planning as language modeling lets GPT-3.5 generate precise driving trajectories from scene descriptions.","strongest_claim":"We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles... the fundamental insight of our approach is the reformulation of motion planning as a language modeling problem.","weakest_assumption":"That an LLM prompted and fine-tuned on language descriptions of coordinates will produce numerically precise, collision-free trajectories in safety-critical, out-of-distribution driving scenes without systematic hallucination or unsafe outputs."}},"verdict_id":"ab952ed4-b768-45fc-b23c-0f647c5eb678"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e39da5beaad828290efb57369564f6a3d0a61ae007f6f1cc66466f7ff2371450","target":"record","created_at":"2026-05-17T23:38:52Z","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":"40efd13105f5f13dc523cb36e44e23762eadac92986e69c1b3f54d0df8f43431","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:59:57Z","title_canon_sha256":"bd8b88211642ffee7a5b88d0a713aeba0091526cf84ee70b61015af5407a6e96"},"schema_version":"1.0","source":{"id":"2310.01415","kind":"arxiv","version":3}},"canonical_sha256":"0296e74829a80e7e528fda76c0f79ba30073cd162829e8088e6a43cbe42a3405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0296e74829a80e7e528fda76c0f79ba30073cd162829e8088e6a43cbe42a3405","first_computed_at":"2026-05-17T23:38:52.291019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.291019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P0qjl+Y5QSXeNVV4Ihghgk4QDyZdkNxx0uUHlbThl8rF0/xCoV1U/HLEQiRFrFsuVQu8gddkqgg8NCs+D644DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.291477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01415","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e39da5beaad828290efb57369564f6a3d0a61ae007f6f1cc66466f7ff2371450","sha256:ed10b572462c669636c344753c667b146592a479a531cdc2b06c2edf77284128"],"state_sha256":"5c8a186d773989750f2fbd4152a5d7f528438da5bfa85964542652a1f06fcec4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrIzXep/Y0kLMMYtn4KBCiqJQhFpr7nl/qiKPxVyEDYtWppJsdkLvxc9B+CPxT69iPJFIimAGupMVCjuP3R8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T06:35:52.676699Z","bundle_sha256":"d34aecab7f442ff23d69901d1310fb671f578db7bbcb36c0b423b82659b29c53"}}