{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G2D4APTF3ECJ5I35GV4FWMALUB","short_pith_number":"pith:G2D4APTF","schema_version":"1.0","canonical_sha256":"3687c03e65d9049ea37d35785b300ba06ad12bfa06dc974e7b69d326a40eb0c5","source":{"kind":"arxiv","id":"2502.14706","version":3},"attestation_state":"computed","paper":{"title":"Building reliable sim driving agents by scaling self-play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Aarav Pandya, Daphne Cornelisse, Eugene Vinitsky, Joseph Su\\'arez, Kevin Joseph","submitted_at":"2025-02-20T16:30:45Z","abstract_excerpt":"Simulation agents are essential for designing and testing systems that interact with humans, such as autonomous vehicles (AVs). These agents serve various purposes, from benchmarking AV performance to stress-testing system limits, but all applications share one key requirement: reliability. To enable sound experimentation, a simulation agent must behave as intended. It should minimize actions that may lead to undesired outcomes, such as collisions, which can distort the signal-to-noise ratio in analyses. As a foundation for reliable sim agents, we propose scaling self-play to thousands of scen"},"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":"2502.14706","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-20T16:30:45Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"cfcfcbc72f3ca8f6ec34fd39c274e48a497d5bfe043890c01243cf57dae0221a","abstract_canon_sha256":"2d8cd80bf3e4eae6bb76dcd84cd80c70f336e21c843ca1ea7fbf1614d1134d30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:40.543193Z","signature_b64":"imBW6X5JBS04fBESD/ghY8LNVJAm2TWZQ0Yh7gn6H8timNA5BlyRIVMFuoFistMYT/Pw59M7yFgbaH+zCctpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3687c03e65d9049ea37d35785b300ba06ad12bfa06dc974e7b69d326a40eb0c5","last_reissued_at":"2026-07-05T11:05:40.542705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:40.542705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building reliable sim driving agents by scaling self-play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Aarav Pandya, Daphne Cornelisse, Eugene Vinitsky, Joseph Su\\'arez, Kevin Joseph","submitted_at":"2025-02-20T16:30:45Z","abstract_excerpt":"Simulation agents are essential for designing and testing systems that interact with humans, such as autonomous vehicles (AVs). These agents serve various purposes, from benchmarking AV performance to stress-testing system limits, but all applications share one key requirement: reliability. To enable sound experimentation, a simulation agent must behave as intended. It should minimize actions that may lead to undesired outcomes, such as collisions, which can distort the signal-to-noise ratio in analyses. As a foundation for reliable sim agents, we propose scaling self-play to thousands of scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14706","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/2502.14706/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":"2502.14706","created_at":"2026-07-05T11:05:40.542764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14706v3","created_at":"2026-07-05T11:05:40.542764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14706","created_at":"2026-07-05T11:05:40.542764+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2D4APTF3ECJ","created_at":"2026-07-05T11:05:40.542764+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2D4APTF3ECJ5I35","created_at":"2026-07-05T11:05:40.542764+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2D4APTF","created_at":"2026-07-05T11:05:40.542764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19641","citing_title":"Scaling Self-Play for End-to-End Driving","ref_index":19,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04149","citing_title":"CoPark: Learning Reactive Parking via Self-Play","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31106","citing_title":"What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25280","citing_title":"EvoFlock: evolved inverse design of multi-agent motion","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05812","citing_title":"Toward Efficient and Robust Behavior Models for Multi-Agent Driving Simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09153","citing_title":"Beyond Self-Play: Hierarchical Reasoning for Continuous Motion in Closed-Loop Traffic Simulation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB","json":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB.json","graph_json":"https://pith.science/api/pith-number/G2D4APTF3ECJ5I35GV4FWMALUB/graph.json","events_json":"https://pith.science/api/pith-number/G2D4APTF3ECJ5I35GV4FWMALUB/events.json","paper":"https://pith.science/paper/G2D4APTF"},"agent_actions":{"view_html":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB","download_json":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB.json","view_paper":"https://pith.science/paper/G2D4APTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14706&json=true","fetch_graph":"https://pith.science/api/pith-number/G2D4APTF3ECJ5I35GV4FWMALUB/graph.json","fetch_events":"https://pith.science/api/pith-number/G2D4APTF3ECJ5I35GV4FWMALUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB/action/storage_attestation","attest_author":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB/action/author_attestation","sign_citation":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB/action/citation_signature","submit_replication":"https://pith.science/pith/G2D4APTF3ECJ5I35GV4FWMALUB/action/replication_record"}},"created_at":"2026-07-05T11:05:40.542764+00:00","updated_at":"2026-07-05T11:05:40.542764+00:00"}