{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OHWF4I4TYR4Q2YGBDH4WJAKMLM","short_pith_number":"pith:OHWF4I4T","schema_version":"1.0","canonical_sha256":"71ec5e2393c4790d60c119f964814c5b102dda94ab6c4e7ff0173c5c8d7a440d","source":{"kind":"arxiv","id":"2106.11810","version":4},"attestation_state":"computed","paper":{"title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NuPlan establishes the first closed-loop benchmark for machine learning planners in autonomous driving.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Lang, Eric Wolff, Holger Caesar, Juraj Kabzan, Kok Seang Tan, Luke Fletcher, Oscar Beijbom, Sammy Omari, Whye Kit Fong","submitted_at":"2021-06-22T14:24:55Z","abstract_excerpt":"In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-s"},"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":"2106.11810","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T14:24:55Z","cross_cats_sorted":[],"title_canon_sha256":"dc5b7ba36498f684b928c4f9cd994b1b27aeaa522c3c1ce6be58b18844e67273","abstract_canon_sha256":"5bf6c22d6748d61fbbb4dad4fb81fd0042769c071faa2e8b3bb4ee792f2a18ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.947499Z","signature_b64":"a/4TI7y4u/uo2WrGvRz1ivtTZwxsbEEcsLxl7zUbMj7tuWANcmjXvLsrAyEEg71Vc2FkoWSFaUzOLnGIEDxHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71ec5e2393c4790d60c119f964814c5b102dda94ab6c4e7ff0173c5c8d7a440d","last_reissued_at":"2026-05-17T23:38:52.946943Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.946943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NuPlan establishes the first closed-loop benchmark for machine learning planners in autonomous driving.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Lang, Eric Wolff, Holger Caesar, Juraj Kabzan, Kok Seang Tan, Luke Fletcher, Oscar Beijbom, Sammy Omari, Whye Kit Fong","submitted_at":"2021-06-22T14:24:55Z","abstract_excerpt":"In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen metrics and reactive-agent simulator will produce rankings that correlate with real-world safety and performance once deployed on physical vehicles.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NuPlan is the first closed-loop benchmark for ML-based autonomous vehicle planning, with 1500h multi-city driving data, reactive simulation, and scenario-specific metrics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NuPlan establishes the first closed-loop benchmark for machine learning planners in autonomous driving.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"975e888e3c7661148de1dda04310d4319b4febc572c6fa8b77eff698bdf1096e"},"source":{"id":"2106.11810","kind":"arxiv","version":4},"verdict":{"id":"93df7ad5-d461-4b9d-af8d-a84d91ccee7a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:57:39.837798Z","strongest_claim":"In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving.","one_line_summary":"NuPlan is the first closed-loop benchmark for ML-based autonomous vehicle planning, with 1500h multi-city driving data, reactive simulation, and scenario-specific metrics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen metrics and reactive-agent simulator will produce rankings that correlate with real-world safety and performance once deployed on physical vehicles.","pith_extraction_headline":"NuPlan establishes the first closed-loop benchmark for machine learning planners in autonomous driving."},"references":{"count":24,"sample":[{"doi":"","year":2017,"title":"CommonRoad: Composable benchmarks for motion plan- ning on roads","work_id":"25af57e2-ac60-41a9-bded-f3495a3658f9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Chauf- feurnet: Learning to drive by imitating the best and synthe- sizing the worst","work_id":"de43fcae-ee6a-49c5-b229-01a0ce8e9804","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Learning to drive from simulation without real world labels","work_id":"6a3833a4-2967-48ba-b3df-f714fddced35","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Gi- ancarlo Baldan, and Oscar Beijbom","work_id":"de934989-2ff8-49f5-a3b3-0fe39f4a14c2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"MP3: A unified model to map, perceive, predict and plan","work_id":"ffea778c-e8d9-4a0e-b307-aed0f162ae7d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":24,"snapshot_sha256":"c44d7de0fc6611a2c42f361a188d449d6663762170b4e5f8b94b9bb1332021e3","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"415d64bdf6099cc2c8f1e608edf4435de561ce19819a59cd2a2953729d095917"},"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":"2106.11810","created_at":"2026-05-17T23:38:52.947048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11810v4","created_at":"2026-05-17T23:38:52.947048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11810","created_at":"2026-05-17T23:38:52.947048+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHWF4I4TYR4Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHWF4I4TYR4Q2YGB","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHWF4I4T","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":37,"sample":[{"citing_arxiv_id":"2506.00560","citing_title":"Using Ensemble Diffusion to Estimate Uncertainty for End-to-End Autonomous Driving","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02450","citing_title":"CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17209","citing_title":"LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22801","citing_title":"Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18059","citing_title":"Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19033","citing_title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19771","citing_title":"Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19631","citing_title":"HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16737","citing_title":"DriveSafer: End-to-End Autonomous Driving with Safety Guidance","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2507.04049","citing_title":"DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2406.08481","citing_title":"Enhancing End-to-End Autonomous Driving with Latent World Model","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07661","citing_title":"Optimization-Guided Diffusion for Interactive Scene Generation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23607","citing_title":"LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10426","citing_title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29908","citing_title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2406.06978","citing_title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01044","citing_title":"A global dataset of continuous urban dashcam driving","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08528","citing_title":"SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM","json":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM.json","graph_json":"https://pith.science/api/pith-number/OHWF4I4TYR4Q2YGBDH4WJAKMLM/graph.json","events_json":"https://pith.science/api/pith-number/OHWF4I4TYR4Q2YGBDH4WJAKMLM/events.json","paper":"https://pith.science/paper/OHWF4I4T"},"agent_actions":{"view_html":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM","download_json":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM.json","view_paper":"https://pith.science/paper/OHWF4I4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11810&json=true","fetch_graph":"https://pith.science/api/pith-number/OHWF4I4TYR4Q2YGBDH4WJAKMLM/graph.json","fetch_events":"https://pith.science/api/pith-number/OHWF4I4TYR4Q2YGBDH4WJAKMLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM/action/storage_attestation","attest_author":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM/action/author_attestation","sign_citation":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM/action/citation_signature","submit_replication":"https://pith.science/pith/OHWF4I4TYR4Q2YGBDH4WJAKMLM/action/replication_record"}},"created_at":"2026-05-17T23:38:52.947048+00:00","updated_at":"2026-05-17T23:38:52.947048+00:00"}