{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N32XEUUBVHUCATS3G7GHNOALJJ","short_pith_number":"pith:N32XEUUB","schema_version":"1.0","canonical_sha256":"6ef5725281a9e8204e5b37cc76b80b4a4a4f033311a1e077f1ae491084b18f94","source":{"kind":"arxiv","id":"2012.06733","version":1},"attestation_state":"computed","paper":{"title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Danfei Xu, Li Fei-Fei, Roberto Mart\\'in-Mart\\'in, Silvio Savarese, Yuke Zhu","submitted_at":"2020-12-12T05:30:35Z","abstract_excerpt":"Imitation Learning is a promising paradigm for learning complex robot manipulation skills by reproducing behavior from human demonstrations. However, manipulation tasks often contain bottleneck regions that require a sequence of precise actions to make meaningful progress, such as a robot inserting a pod into a coffee machine to make coffee. Trained policies can fail in these regions because small deviations in actions can lead the policy into states not covered by the demonstrations. Intervention-based policy learning is an alternative that can address this issue -- it allows human operators "},"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":"2012.06733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-12T05:30:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"47deff9749fe08381e8b8e3c0cbfb12e86e1ee21c485c798219555b63f0bbb11","abstract_canon_sha256":"357c4803de9486a332152ca14d0d01fd0314aa7d8428cc7e1381b7744ba14d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:58.819333Z","signature_b64":"PZZ8ayLkKpH3brWtpeTWNyQGmnEiqLD/rPKowspyTySRTRNEf5dvzOYEi6Lh0rue38eS70ZEw9DzhMBrptt0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef5725281a9e8204e5b37cc76b80b4a4a4f033311a1e077f1ae491084b18f94","last_reissued_at":"2026-07-05T01:58:58.818815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:58.818815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Danfei Xu, Li Fei-Fei, Roberto Mart\\'in-Mart\\'in, Silvio Savarese, Yuke Zhu","submitted_at":"2020-12-12T05:30:35Z","abstract_excerpt":"Imitation Learning is a promising paradigm for learning complex robot manipulation skills by reproducing behavior from human demonstrations. However, manipulation tasks often contain bottleneck regions that require a sequence of precise actions to make meaningful progress, such as a robot inserting a pod into a coffee machine to make coffee. Trained policies can fail in these regions because small deviations in actions can lead the policy into states not covered by the demonstrations. Intervention-based policy learning is an alternative that can address this issue -- it allows human operators "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06733","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/2012.06733/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":"2012.06733","created_at":"2026-07-05T01:58:58.818877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06733v1","created_at":"2026-07-05T01:58:58.818877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06733","created_at":"2026-07-05T01:58:58.818877+00:00"},{"alias_kind":"pith_short_12","alias_value":"N32XEUUBVHUC","created_at":"2026-07-05T01:58:58.818877+00:00"},{"alias_kind":"pith_short_16","alias_value":"N32XEUUBVHUCATS3","created_at":"2026-07-05T01:58:58.818877+00:00"},{"alias_kind":"pith_short_8","alias_value":"N32XEUUB","created_at":"2026-07-05T01:58:58.818877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26603","citing_title":"Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01651","citing_title":"One Demonstration Is Enough for Real-World Robotic Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12372","citing_title":"UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31286","citing_title":"DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31494","citing_title":"Robustness of Robotic Manipulation: Foundations and Frontiers","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21710","citing_title":"PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15157","citing_title":"Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2403.01823","citing_title":"RT-H: Action Hierarchies Using Language","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15157","citing_title":"Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09410","citing_title":"RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14734","citing_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ","json":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ.json","graph_json":"https://pith.science/api/pith-number/N32XEUUBVHUCATS3G7GHNOALJJ/graph.json","events_json":"https://pith.science/api/pith-number/N32XEUUBVHUCATS3G7GHNOALJJ/events.json","paper":"https://pith.science/paper/N32XEUUB"},"agent_actions":{"view_html":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ","download_json":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ.json","view_paper":"https://pith.science/paper/N32XEUUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06733&json=true","fetch_graph":"https://pith.science/api/pith-number/N32XEUUBVHUCATS3G7GHNOALJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/N32XEUUBVHUCATS3G7GHNOALJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ/action/storage_attestation","attest_author":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ/action/author_attestation","sign_citation":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ/action/citation_signature","submit_replication":"https://pith.science/pith/N32XEUUBVHUCATS3G7GHNOALJJ/action/replication_record"}},"created_at":"2026-07-05T01:58:58.818877+00:00","updated_at":"2026-07-05T01:58:58.818877+00:00"}