{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LPURC2L6AUUQEYNWRKPG7ACIOP","short_pith_number":"pith:LPURC2L6","schema_version":"1.0","canonical_sha256":"5be911697e05290261b68a9e6f804873dbb13d6a29edaab8de3180d27be52a7c","source":{"kind":"arxiv","id":"2407.15007","version":2},"attestation_state":"computed","paper":{"title":"Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Adam Block, Dipendra Misra, Dylan J. Foster","submitted_at":"2024-07-20T23:31:56Z","abstract_excerpt":"Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC), is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner's access to the expert.\n  We revisit the apparent gap between o"},"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":"2407.15007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-20T23:31:56Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"cb9719f26d0de87eed28e7babaddcc7ee802556fb2d1af36ba4a27d50b2d2bde","abstract_canon_sha256":"2216f45fc528ba8930770930b975665902f4f9809bb24220c5ace731d0c109b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.164535Z","signature_b64":"exwSxwYbXTUHoYnvfrx/i6vnqicLYADepKgijRaD8HQBO8X8rBjALpRppKXZ2QksaMGBW4+vnQoc8p4HWqbIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5be911697e05290261b68a9e6f804873dbb13d6a29edaab8de3180d27be52a7c","last_reissued_at":"2026-07-05T09:42:28.164029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.164029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Adam Block, Dipendra Misra, Dylan J. Foster","submitted_at":"2024-07-20T23:31:56Z","abstract_excerpt":"Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC), is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner's access to the expert.\n  We revisit the apparent gap between o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15007","kind":"arxiv","version":2},"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/2407.15007/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":"2407.15007","created_at":"2026-07-05T09:42:28.164086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15007v2","created_at":"2026-07-05T09:42:28.164086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15007","created_at":"2026-07-05T09:42:28.164086+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPURC2L6AUUQ","created_at":"2026-07-05T09:42:28.164086+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPURC2L6AUUQEYNW","created_at":"2026-07-05T09:42:28.164086+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPURC2L6","created_at":"2026-07-05T09:42:28.164086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12000","citing_title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12000","citing_title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01778","citing_title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP","json":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP.json","graph_json":"https://pith.science/api/pith-number/LPURC2L6AUUQEYNWRKPG7ACIOP/graph.json","events_json":"https://pith.science/api/pith-number/LPURC2L6AUUQEYNWRKPG7ACIOP/events.json","paper":"https://pith.science/paper/LPURC2L6"},"agent_actions":{"view_html":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP","download_json":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP.json","view_paper":"https://pith.science/paper/LPURC2L6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15007&json=true","fetch_graph":"https://pith.science/api/pith-number/LPURC2L6AUUQEYNWRKPG7ACIOP/graph.json","fetch_events":"https://pith.science/api/pith-number/LPURC2L6AUUQEYNWRKPG7ACIOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP/action/storage_attestation","attest_author":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP/action/author_attestation","sign_citation":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP/action/citation_signature","submit_replication":"https://pith.science/pith/LPURC2L6AUUQEYNWRKPG7ACIOP/action/replication_record"}},"created_at":"2026-07-05T09:42:28.164086+00:00","updated_at":"2026-07-05T09:42:28.164086+00:00"}