{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUMYKSR74ZAYOLM2FTE775KAD2","short_pith_number":"pith:WUMYKSR7","schema_version":"1.0","canonical_sha256":"b519854a3fe641872d9a2cc9fff5401e9cd4a492cba5a529daca1605f6176e25","source":{"kind":"arxiv","id":"2510.12796","version":2},"attestation_state":"computed","paper":{"title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Adding world modeling to predict future images lets vision-language-action models use large driving datasets more effectively and accelerate performance gains as data scales.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bing Zhan, Chufeng Tang, Haochen Wang, Lue Fan, Lu Hou, Shuyao Shang, Weisong Liu, Xiaoman Wang, Yasong An, Yingyan Li, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","submitted_at":"2025-10-14T17:59:47Z","abstract_excerpt":"Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose \\textbf{DriveVLA-W0}, a training paradigm that employs world modeling to predict future images. This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment. We "},"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":"2510.12796","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-14T17:59:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d6fd76fc2dd6307b1b71f8456c10fcefcf50453f3ad221fbbd9a0ed2deee3a4","abstract_canon_sha256":"b0c36fc3151591d8a7b9a6ce74f682f50eb4bcf76c0dc2eaedbfb740b51fb4c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.790072Z","signature_b64":"sa/EH0jNsHgde/0PlWKyaSWADuc2YMGDlF2l1nbsatRhgSAbE+uWXng1nOJ4Qn/JvkSAuDF+oo5q+EPVcbL5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b519854a3fe641872d9a2cc9fff5401e9cd4a492cba5a529daca1605f6176e25","last_reissued_at":"2026-05-17T23:38:14.789505Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.789505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Adding world modeling to predict future images lets vision-language-action models use large driving datasets more effectively and accelerate performance gains as data scales.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bing Zhan, Chufeng Tang, Haochen Wang, Lue Fan, Lu Hou, Shuyao Shang, Weisong Liu, Xiaoman Wang, Yasong An, Yingyan Li, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","submitted_at":"2025-10-14T17:59:47Z","abstract_excerpt":"Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose \\textbf{DriveVLA-W0}, a training paradigm that employs world modeling to predict future images. This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment. We "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we propose DriveVLA-W0, a training paradigm that employs world modeling to predict future images. ... Crucially, it amplifies the data scaling law, showing that performance gains accelerate as the training dataset size increases.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the added world modeling task of predicting future images supplies a dense, unbiased self-supervised signal that meaningfully utilizes unused model capacity without requiring extra labels or introducing new failure modes in driving dynamics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DriveVLA-W0 adds world modeling to predict future images in VLA models, overcoming sparse action supervision and amplifying data scaling laws on NAVSIM benchmarks and a large in-house dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Adding world modeling to predict future images lets vision-language-action models use large driving datasets more effectively and accelerate performance gains as data scales.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b1bf9098c357bc593fcd6e5671323d349b63e1254a40e7a4893235c251225b2a"},"source":{"id":"2510.12796","kind":"arxiv","version":2},"verdict":{"id":"cf6793d1-473e-4e13-9da8-1ff37c4b0c32","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T06:42:20.341660Z","strongest_claim":"we propose DriveVLA-W0, a training paradigm that employs world modeling to predict future images. ... Crucially, it amplifies the data scaling law, showing that performance gains accelerate as the training dataset size increases.","one_line_summary":"DriveVLA-W0 adds world modeling to predict future images in VLA models, overcoming sparse action supervision and amplifying data scaling laws on NAVSIM benchmarks and a large in-house dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the added world modeling task of predicting future images supplies a dense, unbiased self-supervised signal that meaningfully utilizes unused model capacity without requiring extra labels or introducing new failure modes in driving dynamics.","pith_extraction_headline":"Adding world modeling to predict future images lets vision-language-action models use large driving datasets more effectively and accelerate performance gains as data scales."},"references":{"count":39,"sample":[{"doi":"","year":2025,"title":"Covla: Comprehensive vision-language-action dataset for autonomous driving","work_id":"6783599d-5a5e-4a21-a4b0-e2ed5582cf30","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":null,"title":"Scaling Laws of Mo- tion Forecasting and Planning – Technical Report","work_id":"dfe35d03-cdc6-4f73-940e-1ae1ceb82a53","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Vavim and vavam: Autonomous driving through video generative modeling","work_id":"b75ea66d-dafb-43ec-9345-f50eb3d615e2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","ref_index":6,"cited_arxiv_id":"2410.24164","is_internal_anchor":true}],"resolved_work":39,"snapshot_sha256":"81a2968186f58f7db9dd6e0c27c178cccb4f6c53537cbf5a001d03d57aa9f2f7","internal_anchors":15},"formal_canon":{"evidence_count":2,"snapshot_sha256":"854227cfb28bcd6bbc663def7c2d1a8978711bed00d69c4e32b3263629f9c637"},"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":"2510.12796","created_at":"2026-05-17T23:38:14.789602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.12796v2","created_at":"2026-05-17T23:38:14.789602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12796","created_at":"2026-05-17T23:38:14.789602+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUMYKSR74ZAY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUMYKSR74ZAYOLM2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUMYKSR7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2605.23270","citing_title":"ChainFlow-VLA: Causal Flow Planning with Vision-Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22089","citing_title":"LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21061","citing_title":"Grounding Driving VLA via Inverse Kinematics","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15120","citing_title":"CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17284","citing_title":"CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous Driving","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2511.23369","citing_title":"SimScale: Learning to Drive via Real-World Simulation at Scale","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2602.19035","citing_title":"OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14696","citing_title":"EponaV2: Driving World Model with Comprehensive Future Reasoning","ref_index":36,"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":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12625","citing_title":"Driving Intents Amplify Planning-Oriented Reinforcement Learning","ref_index":11,"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":65,"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":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12625","citing_title":"Driving Intents Amplify Planning-Oriented Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":34,"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":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":111,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":25,"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":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09701","citing_title":"DriveFuture: Future-Aware Latent World Models for Autonomous Driving","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":111,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04470","citing_title":"CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies","ref_index":7,"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":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07990","citing_title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2","json":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2.json","graph_json":"https://pith.science/api/pith-number/WUMYKSR74ZAYOLM2FTE775KAD2/graph.json","events_json":"https://pith.science/api/pith-number/WUMYKSR74ZAYOLM2FTE775KAD2/events.json","paper":"https://pith.science/paper/WUMYKSR7"},"agent_actions":{"view_html":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2","download_json":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2.json","view_paper":"https://pith.science/paper/WUMYKSR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.12796&json=true","fetch_graph":"https://pith.science/api/pith-number/WUMYKSR74ZAYOLM2FTE775KAD2/graph.json","fetch_events":"https://pith.science/api/pith-number/WUMYKSR74ZAYOLM2FTE775KAD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2/action/storage_attestation","attest_author":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2/action/author_attestation","sign_citation":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2/action/citation_signature","submit_replication":"https://pith.science/pith/WUMYKSR74ZAYOLM2FTE775KAD2/action/replication_record"}},"created_at":"2026-05-17T23:38:14.789602+00:00","updated_at":"2026-05-17T23:38:14.789602+00:00"}