{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G3JDEEB5JWSURYLXO47IDVNIVV","short_pith_number":"pith:G3JDEEB5","schema_version":"1.0","canonical_sha256":"36d232103d4da548e177773e81d5a8ad6314c593ae2821744a27d3a962b216ce","source":{"kind":"arxiv","id":"2007.00178","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrien Gaidon, Allan Raventos, Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Guy Rosman, Woodrow Z. Wang, Zhangjie Cao","submitted_at":"2020-07-01T01:41:45Z","abstract_excerpt":"Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In such near-accident scenarios, even a minor change in the vehicle's actions may result in drastically different consequences. To avoid unsafe actions in near-accident scenarios, we need to fully explore the environment. However, reinforcement learning (RL) and imitation learning (IL), two widely-used policy learning methods, cannot model rapid phase transitions and are not scalable to fully cover all the states. To add"},"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":"2007.00178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T01:41:45Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"7f783dd8f8a8385ff4fe0471a1d6059567db36d4b8fb8e50484c0a2e82d62590","abstract_canon_sha256":"42383d9190384095e4799d8959545de7a0edec7daff1fd4456a3ce6e547ac366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:29.125899Z","signature_b64":"YKZVj1ChGWznNaNoELahxROOLSSVp2l8vU8GqUCh9MNyunfKEyGeo2AVvAJ6FUIq4DsuCYrHLGmXngbw+SgRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d232103d4da548e177773e81d5a8ad6314c593ae2821744a27d3a962b216ce","last_reissued_at":"2026-07-05T01:15:29.125434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:29.125434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrien Gaidon, Allan Raventos, Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Guy Rosman, Woodrow Z. Wang, Zhangjie Cao","submitted_at":"2020-07-01T01:41:45Z","abstract_excerpt":"Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In such near-accident scenarios, even a minor change in the vehicle's actions may result in drastically different consequences. To avoid unsafe actions in near-accident scenarios, we need to fully explore the environment. However, reinforcement learning (RL) and imitation learning (IL), two widely-used policy learning methods, cannot model rapid phase transitions and are not scalable to fully cover all the states. To add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00178","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/2007.00178/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":"2007.00178","created_at":"2026-07-05T01:15:29.125485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.00178v1","created_at":"2026-07-05T01:15:29.125485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00178","created_at":"2026-07-05T01:15:29.125485+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3JDEEB5JWSU","created_at":"2026-07-05T01:15:29.125485+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3JDEEB5JWSURYLX","created_at":"2026-07-05T01:15:29.125485+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3JDEEB5","created_at":"2026-07-05T01:15:29.125485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00624","citing_title":"Vehicle-in-Virtual-Environment (VVE) Method for Developing and Evaluating VRU Safety of Connected and Autonomous Driving with Focus on Bicyclist Safety","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV","json":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV.json","graph_json":"https://pith.science/api/pith-number/G3JDEEB5JWSURYLXO47IDVNIVV/graph.json","events_json":"https://pith.science/api/pith-number/G3JDEEB5JWSURYLXO47IDVNIVV/events.json","paper":"https://pith.science/paper/G3JDEEB5"},"agent_actions":{"view_html":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV","download_json":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV.json","view_paper":"https://pith.science/paper/G3JDEEB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.00178&json=true","fetch_graph":"https://pith.science/api/pith-number/G3JDEEB5JWSURYLXO47IDVNIVV/graph.json","fetch_events":"https://pith.science/api/pith-number/G3JDEEB5JWSURYLXO47IDVNIVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV/action/storage_attestation","attest_author":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV/action/author_attestation","sign_citation":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV/action/citation_signature","submit_replication":"https://pith.science/pith/G3JDEEB5JWSURYLXO47IDVNIVV/action/replication_record"}},"created_at":"2026-07-05T01:15:29.125485+00:00","updated_at":"2026-07-05T01:15:29.125485+00:00"}