{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MUANCWBXZ5CDLXQPHJV6VYZSP","short_pith_number":"pith:3MUANCWB","schema_version":"1.0","canonical_sha256":"db28068ac1be7a21aef079d35f571993e0d8bf7787b4b2ff6975ed94b826322d","source":{"kind":"arxiv","id":"2412.14415","version":3},"attestation_state":"computed","paper":{"title":"DriveGPT: Scaling Autoregressive Behavior Models for Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Brian Pierce, Chingiz Tairbekov, David S. Hayden, Eric M. Wolff, Hongge Chen, Mark Edmonds, Paul Vernaza, Pratik Agarwal, Pratik Elias Jacob, Siddhartha Srinivasa, Tianshi Gao, Tung Phan-Minh, Xiaobai Chen, Xin Huang, Xinxin Chen, Yuning Chai","submitted_at":"2024-12-19T00:06:09Z","abstract_excerpt":"We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios"},"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":"2412.14415","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T00:06:09Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"cc00e5f5aa83ca0b7ef1a258700691987c5c8e4ebddceddd659741b283de732e","abstract_canon_sha256":"dbe24f24fbdcd50c3835e95e53c55b7276577877ad447cabe87eabdd405e383b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:30.707303Z","signature_b64":"EmIqntgdFhZbG8CQbQUPjN32MYorgHmnosM+RHhKLmjEvI8CxBiMo9QlAEd3guyqLfRhPM2NUvZnKR6EqdA5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db28068ac1be7a21aef079d35f571993e0d8bf7787b4b2ff6975ed94b826322d","last_reissued_at":"2026-07-05T10:57:30.706817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:30.706817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveGPT: Scaling Autoregressive Behavior Models for Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Brian Pierce, Chingiz Tairbekov, David S. Hayden, Eric M. Wolff, Hongge Chen, Mark Edmonds, Paul Vernaza, Pratik Agarwal, Pratik Elias Jacob, Siddhartha Srinivasa, Tianshi Gao, Tung Phan-Minh, Xiaobai Chen, Xin Huang, Xinxin Chen, Yuning Chai","submitted_at":"2024-12-19T00:06:09Z","abstract_excerpt":"We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14415","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.14415/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2412.14415","created_at":"2026-07-05T10:57:30.706876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14415v3","created_at":"2026-07-05T10:57:30.706876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14415","created_at":"2026-07-05T10:57:30.706876+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MUANCWBXZ5C","created_at":"2026-07-05T10:57:30.706876+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MUANCWBXZ5CDLXQ","created_at":"2026-07-05T10:57:30.706876+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MUANCWB","created_at":"2026-07-05T10:57:30.706876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.23369","citing_title":"SimScale: Learning to Drive via Real-World Simulation at Scale","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP","json":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP.json","graph_json":"https://pith.science/api/pith-number/3MUANCWBXZ5CDLXQPHJV6VYZSP/graph.json","events_json":"https://pith.science/api/pith-number/3MUANCWBXZ5CDLXQPHJV6VYZSP/events.json","paper":"https://pith.science/paper/3MUANCWB"},"agent_actions":{"view_html":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP","download_json":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP.json","view_paper":"https://pith.science/paper/3MUANCWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14415&json=true","fetch_graph":"https://pith.science/api/pith-number/3MUANCWBXZ5CDLXQPHJV6VYZSP/graph.json","fetch_events":"https://pith.science/api/pith-number/3MUANCWBXZ5CDLXQPHJV6VYZSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP/action/storage_attestation","attest_author":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP/action/author_attestation","sign_citation":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP/action/citation_signature","submit_replication":"https://pith.science/pith/3MUANCWBXZ5CDLXQPHJV6VYZSP/action/replication_record"}},"created_at":"2026-07-05T10:57:30.706876+00:00","updated_at":"2026-07-05T10:57:30.706876+00:00"}