{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FGAYBBHGD2C75GA37OWQVLZWTD","short_pith_number":"pith:FGAYBBHG","schema_version":"1.0","canonical_sha256":"29818084e61e85fe981bfbad0aaf3698f92903a38b85af603cc771a0ad336aa3","source":{"kind":"arxiv","id":"2108.08265","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Liniger, Dengxin Dai, Fisher Yu, Luc Van Gool, Zhejun Zhang","submitted_at":"2021-08-18T17:36:51Z","abstract_excerpt":"End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that demand dense on-policy supervision. On the contrary, automated experts that leverage privileged information can efficiently generate large scale on-policy and off-policy demonstrations. However, existing automated experts for urban driving make heavy use of hand-crafted rules and perform suboptimally even on driving simulators, where ground-truth information is available. To address these issues, we train a reinforcement "},"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":"2108.08265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-18T17:36:51Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"49ec29344577de06a275fe3eec2b9088a688909560dc9347e83192ea0a961422","abstract_canon_sha256":"133dcc1ae26d5dbece751b7d59f0369a2ae4df001fa089c90852bbee9d9345a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:03.351335Z","signature_b64":"GZYkUm6MUTjtF/0NW+jQrJSQx21P2aezCJ6x07BuY6P6tnS6hTa03uxTx4FVqxNW7cCNJ43l2cvhyZucgao9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29818084e61e85fe981bfbad0aaf3698f92903a38b85af603cc771a0ad336aa3","last_reissued_at":"2026-07-05T03:20:03.350837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:03.350837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Liniger, Dengxin Dai, Fisher Yu, Luc Van Gool, Zhejun Zhang","submitted_at":"2021-08-18T17:36:51Z","abstract_excerpt":"End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that demand dense on-policy supervision. On the contrary, automated experts that leverage privileged information can efficiently generate large scale on-policy and off-policy demonstrations. However, existing automated experts for urban driving make heavy use of hand-crafted rules and perform suboptimally even on driving simulators, where ground-truth information is available. To address these issues, we train a reinforcement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08265","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/2108.08265/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":"2108.08265","created_at":"2026-07-05T03:20:03.350895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08265v3","created_at":"2026-07-05T03:20:03.350895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08265","created_at":"2026-07-05T03:20:03.350895+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGAYBBHGD2C7","created_at":"2026-07-05T03:20:03.350895+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGAYBBHGD2C75GA3","created_at":"2026-07-05T03:20:03.350895+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGAYBBHG","created_at":"2026-07-05T03:20:03.350895+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":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD","json":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD.json","graph_json":"https://pith.science/api/pith-number/FGAYBBHGD2C75GA37OWQVLZWTD/graph.json","events_json":"https://pith.science/api/pith-number/FGAYBBHGD2C75GA37OWQVLZWTD/events.json","paper":"https://pith.science/paper/FGAYBBHG"},"agent_actions":{"view_html":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD","download_json":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD.json","view_paper":"https://pith.science/paper/FGAYBBHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08265&json=true","fetch_graph":"https://pith.science/api/pith-number/FGAYBBHGD2C75GA37OWQVLZWTD/graph.json","fetch_events":"https://pith.science/api/pith-number/FGAYBBHGD2C75GA37OWQVLZWTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD/action/storage_attestation","attest_author":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD/action/author_attestation","sign_citation":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD/action/citation_signature","submit_replication":"https://pith.science/pith/FGAYBBHGD2C75GA37OWQVLZWTD/action/replication_record"}},"created_at":"2026-07-05T03:20:03.350895+00:00","updated_at":"2026-07-05T03:20:03.350895+00:00"}