{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJR6JS25OLRYWTYIB42FZHCGPT","short_pith_number":"pith:DJR6JS25","schema_version":"1.0","canonical_sha256":"1a63e4cb5d72e38b4f080f345c9c467cccbe2a028b5bd98e76a38da8c9ad43ba","source":{"kind":"arxiv","id":"2511.00088","version":2},"attestation_state":"computed","paper":{"title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Boris Ivanovic, Boyi Li, Dongran Liu, Ed Schmerling, Eric Yang, Greg Heinrich, Jack Huang, Jason Lu, Jenna Diamond, Junjie Bai, Ke Chen, Langechuan Liu, Liang Feng, Lindsey Pavao, Marco Pavone, Mike Ranzinger, Ming-Yu Liu, NVIDIA: Yan Wang, Pavlo Molchanov, Peter Karkus, Pinyi Li, Ran Tian, Sarah Tariq, Shida Shen, Tianjun Xiao, Tilman Wekel, Tong Che, Tsung-Yi Lin, Wenhao Ding, Wenjie Luo, Wenyuan Zhang, Xiaodong Yang, Xiaohui Zeng, Xinshuo Weng, Yifan Ding, Yulong Cao, Yunfei Shi, Yunxiang Mao, Yurong You, Yuxiao Chen, Zhenghao Peng, Zhijian Liu","submitted_at":"2025-10-30T01:25:34Z","abstract_excerpt":"End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision"},"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":"2511.00088","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-30T01:25:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"42237854896a2c357fc93f3d701aa336c60818f8d4cf88bbe5a4f577be02b5e8","abstract_canon_sha256":"ae414ab5e7f82a4143e5e4a74dca95d161e092d0e9d2249c22a571061ebe8962"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:29:59.407874Z","signature_b64":"09gyNVI9vrsQg2aUHyWr8A+kv32Kg5V7NJqIWn+FHJp3kjX2Y7qQLHnlpvRxszom/0MqL13AosTFKwnbO58KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a63e4cb5d72e38b4f080f345c9c467cccbe2a028b5bd98e76a38da8c9ad43ba","last_reissued_at":"2026-05-18T02:29:59.407442Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:29:59.407442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Boris Ivanovic, Boyi Li, Dongran Liu, Ed Schmerling, Eric Yang, Greg Heinrich, Jack Huang, Jason Lu, Jenna Diamond, Junjie Bai, Ke Chen, Langechuan Liu, Liang Feng, Lindsey Pavao, Marco Pavone, Mike Ranzinger, Ming-Yu Liu, NVIDIA: Yan Wang, Pavlo Molchanov, Peter Karkus, Pinyi Li, Ran Tian, Sarah Tariq, Shida Shen, Tianjun Xiao, Tilman Wekel, Tong Che, Tsung-Yi Lin, Wenhao Ding, Wenjie Luo, Wenyuan Zhang, Xiaodong Yang, Xiaohui Zeng, Xinshuo Weng, Yifan Ding, Yulong Cao, Yunfei Shi, Yunxiang Mao, Yurong You, Yuxiao Chen, Zhenghao Peng, Zhijian Liu","submitted_at":"2025-10-30T01:25:34Z","abstract_excerpt":"End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.00088","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2511.00088","created_at":"2026-05-18T02:29:59.407500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.00088v2","created_at":"2026-05-18T02:29:59.407500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.00088","created_at":"2026-05-18T02:29:59.407500+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJR6JS25OLRY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJR6JS25OLRYWTYI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJR6JS25","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":18,"sample":[{"citing_arxiv_id":"2512.10226","citing_title":"Latent Chain-of-Thought World Modeling for End-to-End Driving","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2603.00696","citing_title":"DRIV-EX: Counterfactual Explanations for Driving LLMs","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":29,"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":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02714","citing_title":"ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03497","citing_title":"Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08975","citing_title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22260","citing_title":"Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21249","citing_title":"Reasoning About Traversability: Language-Guided Off-Road 3D Trajectory Planning","ref_index":31,"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":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10856","citing_title":"BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08266","citing_title":"Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08031","citing_title":"Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07514","citing_title":"Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17176","citing_title":"Intent-aligned Autonomous Spacecraft Guidance via Reasoning Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":104,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT","json":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT.json","graph_json":"https://pith.science/api/pith-number/DJR6JS25OLRYWTYIB42FZHCGPT/graph.json","events_json":"https://pith.science/api/pith-number/DJR6JS25OLRYWTYIB42FZHCGPT/events.json","paper":"https://pith.science/paper/DJR6JS25"},"agent_actions":{"view_html":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT","download_json":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT.json","view_paper":"https://pith.science/paper/DJR6JS25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.00088&json=true","fetch_graph":"https://pith.science/api/pith-number/DJR6JS25OLRYWTYIB42FZHCGPT/graph.json","fetch_events":"https://pith.science/api/pith-number/DJR6JS25OLRYWTYIB42FZHCGPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT/action/storage_attestation","attest_author":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT/action/author_attestation","sign_citation":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT/action/citation_signature","submit_replication":"https://pith.science/pith/DJR6JS25OLRYWTYIB42FZHCGPT/action/replication_record"}},"created_at":"2026-05-18T02:29:59.407500+00:00","updated_at":"2026-05-18T02:29:59.407500+00:00"}