{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5YGKYPCYXSFNXJE2A6CLOAZDGG","short_pith_number":"pith:5YGKYPCY","schema_version":"1.0","canonical_sha256":"ee0cac3c58bc8adba49a0784b7032331ae44ff5f89b5f21c774c9dbe9881794e","source":{"kind":"arxiv","id":"2504.19077","version":1},"attestation_state":"computed","paper":{"title":"Learning to Drive from a World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Adeeb Shihadeh, Armand du Parc Locmaria, George Hotz, Greg Hogan, Harald Sch\\\"afer, Kacper Raczy, Mitchell Goff, Weixing Zhang, Yassine Yousfi","submitted_at":"2025-04-27T02:17:22Z","abstract_excerpt":"Most self-driving systems rely on hand-coded perception outputs and engineered driving rules. Learning directly from human driving data with an end-to-end method can allow for a training architecture that is simpler and scales well with compute and data.\n  In this work, we propose an end-to-end training architecture that uses real driving data to train a driving policy in an on-policy simulator. We show two different methods of simulation, one with reprojective simulation and one with a learned world model. We show that both methods can be used to train a policy that learns driving behavior wi"},"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":"2504.19077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-27T02:17:22Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a1f7941c28ebb655636005b61bd771779155878ff633e458d252c011a1dce233","abstract_canon_sha256":"639e45d673bbee4feb1807fe803c08fa96809f3fb8e1f4cc8799584d70e528b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:51.671831Z","signature_b64":"1/3NqVBpfUCgoqp7iIGGhMeyJvuu44ceDylYcvwGKSbTb6IZyneciFG6KHOLAYdQO4Dw+6V1scOqDpLX5Iu+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0cac3c58bc8adba49a0784b7032331ae44ff5f89b5f21c774c9dbe9881794e","last_reissued_at":"2026-07-05T10:54:51.671367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:51.671367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Drive from a World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Adeeb Shihadeh, Armand du Parc Locmaria, George Hotz, Greg Hogan, Harald Sch\\\"afer, Kacper Raczy, Mitchell Goff, Weixing Zhang, Yassine Yousfi","submitted_at":"2025-04-27T02:17:22Z","abstract_excerpt":"Most self-driving systems rely on hand-coded perception outputs and engineered driving rules. Learning directly from human driving data with an end-to-end method can allow for a training architecture that is simpler and scales well with compute and data.\n  In this work, we propose an end-to-end training architecture that uses real driving data to train a driving policy in an on-policy simulator. We show two different methods of simulation, one with reprojective simulation and one with a learned world model. We show that both methods can be used to train a policy that learns driving behavior wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19077","kind":"arxiv","version":1},"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/2504.19077/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":"2504.19077","created_at":"2026-07-05T10:54:51.671428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19077v1","created_at":"2026-07-05T10:54:51.671428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19077","created_at":"2026-07-05T10:54:51.671428+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YGKYPCYXSFN","created_at":"2026-07-05T10:54:51.671428+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YGKYPCYXSFNXJE2","created_at":"2026-07-05T10:54:51.671428+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YGKYPCY","created_at":"2026-07-05T10:54:51.671428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.09981","citing_title":"ReSim: Reliable World Simulation for Autonomous Driving","ref_index":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG","json":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG.json","graph_json":"https://pith.science/api/pith-number/5YGKYPCYXSFNXJE2A6CLOAZDGG/graph.json","events_json":"https://pith.science/api/pith-number/5YGKYPCYXSFNXJE2A6CLOAZDGG/events.json","paper":"https://pith.science/paper/5YGKYPCY"},"agent_actions":{"view_html":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG","download_json":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG.json","view_paper":"https://pith.science/paper/5YGKYPCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19077&json=true","fetch_graph":"https://pith.science/api/pith-number/5YGKYPCYXSFNXJE2A6CLOAZDGG/graph.json","fetch_events":"https://pith.science/api/pith-number/5YGKYPCYXSFNXJE2A6CLOAZDGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG/action/storage_attestation","attest_author":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG/action/author_attestation","sign_citation":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG/action/citation_signature","submit_replication":"https://pith.science/pith/5YGKYPCYXSFNXJE2A6CLOAZDGG/action/replication_record"}},"created_at":"2026-07-05T10:54:51.671428+00:00","updated_at":"2026-07-05T10:54:51.671428+00:00"}