{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QKYDEFK5IF3NTF63ZJI67NVC3S","short_pith_number":"pith:QKYDEFK5","schema_version":"1.0","canonical_sha256":"82b032155d4176d997dbca51efb6a2dcb9d1a45e4251da1b7d74b8c9d89057d0","source":{"kind":"arxiv","id":"2210.16567","version":1},"attestation_state":"computed","paper":{"title":"DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ferhat Yurdakul, Feyza Eksen, Halil Durmus, Nazim Kemal Ure, Resul Dagdanov","submitted_at":"2022-10-29T10:58:43Z","abstract_excerpt":"Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX (DeFIX) failures of an Imitation Learning (IL) agent by extracting infraction spots and re-constructing mini-scenarios on these infraction areas to train an RL agent for fixing the shortcomings of the IL approach. DeFIX is a continuous learning framework, where extraction of failure scenarios and training of RL agents are executed in an infinite loop. After "},"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":"2210.16567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-29T10:58:43Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"1ac858a2a9b969e2bfec9ee9cc381cb0164d91284d8cd79a00f1c078744a8c00","abstract_canon_sha256":"11abd40055a5e983cf6ecd187fc39cd293a81b564f151f1a21c721aa9c525441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:00.673359Z","signature_b64":"eLqIoBvc4RiKYWW/pfg3DePLofGhzWdgTtzRf4fC+VNfKRQveaavUYKC3c9OoJRmLkHQJoTUdyy6vHceOl7oBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82b032155d4176d997dbca51efb6a2dcb9d1a45e4251da1b7d74b8c9d89057d0","last_reissued_at":"2026-07-05T11:39:00.672853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:00.672853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ferhat Yurdakul, Feyza Eksen, Halil Durmus, Nazim Kemal Ure, Resul Dagdanov","submitted_at":"2022-10-29T10:58:43Z","abstract_excerpt":"Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX (DeFIX) failures of an Imitation Learning (IL) agent by extracting infraction spots and re-constructing mini-scenarios on these infraction areas to train an RL agent for fixing the shortcomings of the IL approach. DeFIX is a continuous learning framework, where extraction of failure scenarios and training of RL agents are executed in an infinite loop. After "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16567","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/2210.16567/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":"2210.16567","created_at":"2026-07-05T11:39:00.672936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16567v1","created_at":"2026-07-05T11:39:00.672936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16567","created_at":"2026-07-05T11:39:00.672936+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKYDEFK5IF3N","created_at":"2026-07-05T11:39:00.672936+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKYDEFK5IF3NTF63","created_at":"2026-07-05T11:39:00.672936+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKYDEFK5","created_at":"2026-07-05T11:39:00.672936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08221","citing_title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S","json":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S.json","graph_json":"https://pith.science/api/pith-number/QKYDEFK5IF3NTF63ZJI67NVC3S/graph.json","events_json":"https://pith.science/api/pith-number/QKYDEFK5IF3NTF63ZJI67NVC3S/events.json","paper":"https://pith.science/paper/QKYDEFK5"},"agent_actions":{"view_html":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S","download_json":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S.json","view_paper":"https://pith.science/paper/QKYDEFK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16567&json=true","fetch_graph":"https://pith.science/api/pith-number/QKYDEFK5IF3NTF63ZJI67NVC3S/graph.json","fetch_events":"https://pith.science/api/pith-number/QKYDEFK5IF3NTF63ZJI67NVC3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S/action/storage_attestation","attest_author":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S/action/author_attestation","sign_citation":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S/action/citation_signature","submit_replication":"https://pith.science/pith/QKYDEFK5IF3NTF63ZJI67NVC3S/action/replication_record"}},"created_at":"2026-07-05T11:39:00.672936+00:00","updated_at":"2026-07-05T11:39:00.672936+00:00"}