{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KUXHHZV5XTGCH4I46RN6JYSJDO","short_pith_number":"pith:KUXHHZV5","schema_version":"1.0","canonical_sha256":"552e73e6bdbccc23f11cf45be4e2491ba703eb8583e4d1bafa50cc37f5eb9cf1","source":{"kind":"arxiv","id":"2109.00137","version":1},"attestation_state":"computed","paper":{"title":"Implicit Behavioral Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Adrian Wong, Andy Zeng, Ayzaan Wahid, Corey Lynch, Igor Mordatch, Johnny Lee, Jonathan Tompson, Laura Downs, Oscar Ramirez, Pete Florence","submitted_at":"2021-09-01T01:20:25Z","abstract_excerpt":"We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models. We present extensive experiments on this finding, and we provide both intuitive insight and theoretical arguments distinguishing the properties of implicit models compared to their explicit counterparts, particularly with respect to approximating complex, potentially discontinuous and multi-valued (set-valued) functions. On robotic policy learning tasks we show that implicit behavioral cloning "},"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":"2109.00137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-01T01:20:25Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"50a58380f7e896a95bebcc774207b3e191358e56ea82ad21d2f84ffbf0274b9c","abstract_canon_sha256":"29a26f503ef21e170fa5b0fa0ee641d936cbe3b2fd210d130194be73879a1e92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:43.144874Z","signature_b64":"hO6XMB+3X7C1p/KaTOU/mXHsMkzE31hM9mvgAf5w0gFtM6/XjZXYkwrAefs5wNcfYY6C2AdmQS85Ok8PkSnjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552e73e6bdbccc23f11cf45be4e2491ba703eb8583e4d1bafa50cc37f5eb9cf1","last_reissued_at":"2026-07-05T03:10:43.144362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:43.144362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Behavioral Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Adrian Wong, Andy Zeng, Ayzaan Wahid, Corey Lynch, Igor Mordatch, Johnny Lee, Jonathan Tompson, Laura Downs, Oscar Ramirez, Pete Florence","submitted_at":"2021-09-01T01:20:25Z","abstract_excerpt":"We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models. We present extensive experiments on this finding, and we provide both intuitive insight and theoretical arguments distinguishing the properties of implicit models compared to their explicit counterparts, particularly with respect to approximating complex, potentially discontinuous and multi-valued (set-valued) functions. On robotic policy learning tasks we show that implicit behavioral cloning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00137","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/2109.00137/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":"2109.00137","created_at":"2026-07-05T03:10:43.144426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00137v1","created_at":"2026-07-05T03:10:43.144426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00137","created_at":"2026-07-05T03:10:43.144426+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUXHHZV5XTGC","created_at":"2026-07-05T03:10:43.144426+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUXHHZV5XTGCH4I4","created_at":"2026-07-05T03:10:43.144426+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUXHHZV5","created_at":"2026-07-05T03:10:43.144426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01098","citing_title":"Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02117","citing_title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2110.06169","citing_title":"Offline Reinforcement Learning with Implicit Q-Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2304.13705","citing_title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11751","citing_title":"Grounded World Model for Semantically Generalizable Planning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO","json":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO.json","graph_json":"https://pith.science/api/pith-number/KUXHHZV5XTGCH4I46RN6JYSJDO/graph.json","events_json":"https://pith.science/api/pith-number/KUXHHZV5XTGCH4I46RN6JYSJDO/events.json","paper":"https://pith.science/paper/KUXHHZV5"},"agent_actions":{"view_html":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO","download_json":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO.json","view_paper":"https://pith.science/paper/KUXHHZV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00137&json=true","fetch_graph":"https://pith.science/api/pith-number/KUXHHZV5XTGCH4I46RN6JYSJDO/graph.json","fetch_events":"https://pith.science/api/pith-number/KUXHHZV5XTGCH4I46RN6JYSJDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO/action/storage_attestation","attest_author":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO/action/author_attestation","sign_citation":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO/action/citation_signature","submit_replication":"https://pith.science/pith/KUXHHZV5XTGCH4I46RN6JYSJDO/action/replication_record"}},"created_at":"2026-07-05T03:10:43.144426+00:00","updated_at":"2026-07-05T03:10:43.144426+00:00"}