{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EGWDKBWTUUVGU4BAMSL7FSWQNU","short_pith_number":"pith:EGWDKBWT","schema_version":"1.0","canonical_sha256":"21ac3506d3a52a6a70206497f2cad06d368da52f4ed7dc22d28c60767c5c3984","source":{"kind":"arxiv","id":"2408.01584","version":3},"attestation_state":"computed","paper":{"title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR","cs.GR","cs.PF"],"primary_cat":"cs.AI","authors_text":"Aarav Pandya, Brennan Shacklett, Daphne Cornelisse, Eugene Vinitsky, Saman Kazemkhani","submitted_at":"2024-08-02T21:37:46Z","abstract_excerpt":"Multi-agent learning algorithms have been successful at generating superhuman planning in various games but have had limited impact on the design of deployed multi-agent planners. A key bottleneck in applying these techniques to multi-agent planning is that they require billions of steps of experience. To enable the study of multi-agent planning at scale, we present GPUDrive. GPUDrive is a GPU-accelerated, multi-agent simulator built on top of the Madrona Game Engine capable of generating over a million simulation steps per second. Observation, reward, and dynamics functions are written direct"},"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":"2408.01584","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-02T21:37:46Z","cross_cats_sorted":["cs.AR","cs.GR","cs.PF"],"title_canon_sha256":"af88857d726a1b7d5e06d641022dc54b79fa9fc70b3e7b03ea623bf7ec3b0b09","abstract_canon_sha256":"9370bff269c7eb226c6517c57fadf8b67ba2f36cbe405f5e8b76ff143cf9b7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:11.992068Z","signature_b64":"ukeduak8HBtDj96mui90xterkeA0XnDFzesG+A+K+8ZHwHiiLujJwaMb/V6TdXenTGYsui4JEBryClNV7T3bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21ac3506d3a52a6a70206497f2cad06d368da52f4ed7dc22d28c60767c5c3984","last_reissued_at":"2026-07-05T10:16:11.991525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:11.991525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR","cs.GR","cs.PF"],"primary_cat":"cs.AI","authors_text":"Aarav Pandya, Brennan Shacklett, Daphne Cornelisse, Eugene Vinitsky, Saman Kazemkhani","submitted_at":"2024-08-02T21:37:46Z","abstract_excerpt":"Multi-agent learning algorithms have been successful at generating superhuman planning in various games but have had limited impact on the design of deployed multi-agent planners. A key bottleneck in applying these techniques to multi-agent planning is that they require billions of steps of experience. To enable the study of multi-agent planning at scale, we present GPUDrive. GPUDrive is a GPU-accelerated, multi-agent simulator built on top of the Madrona Game Engine capable of generating over a million simulation steps per second. Observation, reward, and dynamics functions are written direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01584","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/2408.01584/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":"2408.01584","created_at":"2026-07-05T10:16:11.991593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01584v3","created_at":"2026-07-05T10:16:11.991593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01584","created_at":"2026-07-05T10:16:11.991593+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGWDKBWTUUVG","created_at":"2026-07-05T10:16:11.991593+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGWDKBWTUUVGU4BA","created_at":"2026-07-05T10:16:11.991593+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGWDKBWT","created_at":"2026-07-05T10:16:11.991593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21587","citing_title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19370","citing_title":"Human-like autonomy emerges from self-play and a pinch of human data","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08340","citing_title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05812","citing_title":"Toward Efficient and Robust Behavior Models for Multi-Agent Driving Simulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08528","citing_title":"SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17032","citing_title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17147","citing_title":"ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU","json":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU.json","graph_json":"https://pith.science/api/pith-number/EGWDKBWTUUVGU4BAMSL7FSWQNU/graph.json","events_json":"https://pith.science/api/pith-number/EGWDKBWTUUVGU4BAMSL7FSWQNU/events.json","paper":"https://pith.science/paper/EGWDKBWT"},"agent_actions":{"view_html":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU","download_json":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU.json","view_paper":"https://pith.science/paper/EGWDKBWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01584&json=true","fetch_graph":"https://pith.science/api/pith-number/EGWDKBWTUUVGU4BAMSL7FSWQNU/graph.json","fetch_events":"https://pith.science/api/pith-number/EGWDKBWTUUVGU4BAMSL7FSWQNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU/action/storage_attestation","attest_author":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU/action/author_attestation","sign_citation":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU/action/citation_signature","submit_replication":"https://pith.science/pith/EGWDKBWTUUVGU4BAMSL7FSWQNU/action/replication_record"}},"created_at":"2026-07-05T10:16:11.991593+00:00","updated_at":"2026-07-05T10:16:11.991593+00:00"}