{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:HQEMQTZ7R26OJ4KLYYTOOSCYGJ","short_pith_number":"pith:HQEMQTZ7","schema_version":"1.0","canonical_sha256":"3c08c84f3f8ebce4f14bc626e748583264c680afe50d67dd68531ec69009308f","source":{"kind":"arxiv","id":"1605.06450","version":1},"attestation_state":"computed","paper":{"title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiakai Zhang, Kyunghyun Cho","submitted_at":"2016-05-20T17:40:16Z","abstract_excerpt":"One way to approach end-to-end autonomous driving is to learn a policy function that maps from a sensory input, such as an image frame from a front-facing camera, to a driving action, by imitating an expert driver, or a reference policy. This can be done by supervised learning, where a policy function is tuned to minimize the difference between the predicted and ground-truth actions. A policy function trained in this way however is known to suffer from unexpected behaviours due to the mismatch between the states reachable by the reference policy and trained policy functions. More advanced algo"},"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":"1605.06450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T17:40:16Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5c95de0b31575b71245a5abf4cc861b3a9dd4cbdb270912e4f6b1f391780a403","abstract_canon_sha256":"023d30bccf8b5f4d1b999098ae7872cdac5e129afa6aa88ecce7c6b57892190b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:18.865371Z","signature_b64":"8ytpabGB+ox7LT9wGjO9i8xJxHLjwhOfg+Fqyzw/n7gT2k9KJySnXnMe317OmGo9klldRnWUU3WCZVYbVbJgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c08c84f3f8ebce4f14bc626e748583264c680afe50d67dd68531ec69009308f","last_reissued_at":"2026-05-18T01:14:18.864690Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:18.864690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiakai Zhang, Kyunghyun Cho","submitted_at":"2016-05-20T17:40:16Z","abstract_excerpt":"One way to approach end-to-end autonomous driving is to learn a policy function that maps from a sensory input, such as an image frame from a front-facing camera, to a driving action, by imitating an expert driver, or a reference policy. This can be done by supervised learning, where a policy function is tuned to minimize the difference between the predicted and ground-truth actions. A policy function trained in this way however is known to suffer from unexpected behaviours due to the mismatch between the states reachable by the reference policy and trained policy functions. More advanced algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06450","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":""},"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":"1605.06450","created_at":"2026-05-18T01:14:18.864807+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06450v1","created_at":"2026-05-18T01:14:18.864807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06450","created_at":"2026-05-18T01:14:18.864807+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQEMQTZ7R26O","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQEMQTZ7R26OJ4KL","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQEMQTZ7","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04038","citing_title":"Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ","json":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ.json","graph_json":"https://pith.science/api/pith-number/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/graph.json","events_json":"https://pith.science/api/pith-number/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/events.json","paper":"https://pith.science/paper/HQEMQTZ7"},"agent_actions":{"view_html":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ","download_json":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ.json","view_paper":"https://pith.science/paper/HQEMQTZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06450&json=true","fetch_graph":"https://pith.science/api/pith-number/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/action/storage_attestation","attest_author":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/action/author_attestation","sign_citation":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/action/citation_signature","submit_replication":"https://pith.science/pith/HQEMQTZ7R26OJ4KLYYTOOSCYGJ/action/replication_record"}},"created_at":"2026-05-18T01:14:18.864807+00:00","updated_at":"2026-05-18T01:14:18.864807+00:00"}