{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TILD75BYBPTOOJWLLUYEQBQLVQ","short_pith_number":"pith:TILD75BY","schema_version":"1.0","canonical_sha256":"9a163ff4380be6e726cb5d3048060bac05f0266cc91a69be10ac52f972b21633","source":{"kind":"arxiv","id":"2205.03195","version":1},"attestation_state":"computed","paper":{"title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Kuefler, Brandyn White, Daewoo Kim, Dragomir Anguelov, Kyriacos Shiarlis, Mark Palatucci, Maximilian Igl, Paul Mougin, Punit Shah, Shimon Whiteson","submitted_at":"2022-05-06T13:21:40Z","abstract_excerpt":"Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such cars. Such models can be obtained by applying learning from demonstration (LfD) to trajectories observed by cars already on the road. However, existing LfD methods are typically insufficient, yielding policies that frequently collide or drive off the road. To address this problem, we propose Symphony, which greatly improves realism by combining conventional policies with a parallel beam search. The beam search refines t"},"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":"2205.03195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-06T13:21:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"7dfbfa3701c08068817f808f847c8be9340cb2c4f51e21d9121a4fbc4a75d9fc","abstract_canon_sha256":"0fea62205bc64bbb0fc6126cc7ea585d6dac121543722039546c56f43315691e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:56.851309Z","signature_b64":"JnXskMDxduTwGdAkF3XQmHLX0s+TSuCWQ517FKKIakqbtpWnpl+8l1PX8vz0BMmfrBSnOFJMWTGgI+Y2ogm0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a163ff4380be6e726cb5d3048060bac05f0266cc91a69be10ac52f972b21633","last_reissued_at":"2026-07-05T04:20:56.850830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:56.850830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Kuefler, Brandyn White, Daewoo Kim, Dragomir Anguelov, Kyriacos Shiarlis, Mark Palatucci, Maximilian Igl, Paul Mougin, Punit Shah, Shimon Whiteson","submitted_at":"2022-05-06T13:21:40Z","abstract_excerpt":"Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such cars. Such models can be obtained by applying learning from demonstration (LfD) to trajectories observed by cars already on the road. However, existing LfD methods are typically insufficient, yielding policies that frequently collide or drive off the road. To address this problem, we propose Symphony, which greatly improves realism by combining conventional policies with a parallel beam search. The beam search refines t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03195","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/2205.03195/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":"2205.03195","created_at":"2026-07-05T04:20:56.850886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03195v1","created_at":"2026-07-05T04:20:56.850886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03195","created_at":"2026-07-05T04:20:56.850886+00:00"},{"alias_kind":"pith_short_12","alias_value":"TILD75BYBPTO","created_at":"2026-07-05T04:20:56.850886+00:00"},{"alias_kind":"pith_short_16","alias_value":"TILD75BYBPTOOJWL","created_at":"2026-07-05T04:20:56.850886+00:00"},{"alias_kind":"pith_short_8","alias_value":"TILD75BY","created_at":"2026-07-05T04:20:56.850886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06987","citing_title":"Response Time Enhances Alignment with Heterogeneous Preferences","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04366","citing_title":"Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ","json":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ.json","graph_json":"https://pith.science/api/pith-number/TILD75BYBPTOOJWLLUYEQBQLVQ/graph.json","events_json":"https://pith.science/api/pith-number/TILD75BYBPTOOJWLLUYEQBQLVQ/events.json","paper":"https://pith.science/paper/TILD75BY"},"agent_actions":{"view_html":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ","download_json":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ.json","view_paper":"https://pith.science/paper/TILD75BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03195&json=true","fetch_graph":"https://pith.science/api/pith-number/TILD75BYBPTOOJWLLUYEQBQLVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TILD75BYBPTOOJWLLUYEQBQLVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ/action/storage_attestation","attest_author":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ/action/author_attestation","sign_citation":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ/action/citation_signature","submit_replication":"https://pith.science/pith/TILD75BYBPTOOJWLLUYEQBQLVQ/action/replication_record"}},"created_at":"2026-07-05T04:20:56.850886+00:00","updated_at":"2026-07-05T04:20:56.850886+00:00"}