{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ","short_pith_number":"pith:Q7K3K5ZM","schema_version":"1.0","canonical_sha256":"87d5b5772c96640f1fab4f26c2e96eaa6cf124962a1995fb1196b1d65c082e64","source":{"kind":"arxiv","id":"2410.21845","version":3},"attestation_state":"computed","paper":{"title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Charles Xu, Jeffrey Wu, Jianlan Luo, Sergey Levine","submitted_at":"2024-10-29T08:12:20Z","abstract_excerpt":"Reinforcement learning (RL) holds great promise for enabling autonomous acquisition of complex robotic manipulation skills, but realizing this potential in real-world settings has been challenging. We present a human-in-the-loop vision-based RL system that demonstrates impressive performance on a diverse set of dexterous manipulation tasks, including dynamic manipulation, precision assembly, and dual-arm coordination. Our approach integrates demonstrations and human corrections, efficient RL algorithms, and other system-level design choices to learn policies that achieve near-perfect success r"},"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":"2410.21845","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T08:12:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87d72f64e9ac3cd3b2641100904a073db3d82783813c744f2040d8f7ba04b07f","abstract_canon_sha256":"1d2e6db4b97cde8ae5a12ec150790c112220fb3fee7758abc845ff73e0cf394d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:39.709882Z","signature_b64":"//mtde81LqYDXNAcOf+jKKyfE0gUqPx9esH1x3pVbdFap8tFGlv429gzap4tnANqno6f4mrVCn0XM9KYfL1gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d5b5772c96640f1fab4f26c2e96eaa6cf124962a1995fb1196b1d65c082e64","last_reissued_at":"2026-07-05T10:35:39.709364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:39.709364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Charles Xu, Jeffrey Wu, Jianlan Luo, Sergey Levine","submitted_at":"2024-10-29T08:12:20Z","abstract_excerpt":"Reinforcement learning (RL) holds great promise for enabling autonomous acquisition of complex robotic manipulation skills, but realizing this potential in real-world settings has been challenging. We present a human-in-the-loop vision-based RL system that demonstrates impressive performance on a diverse set of dexterous manipulation tasks, including dynamic manipulation, precision assembly, and dual-arm coordination. Our approach integrates demonstrations and human corrections, efficient RL algorithms, and other system-level design choices to learn policies that achieve near-perfect success r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21845","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/2410.21845/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":"2410.21845","created_at":"2026-07-05T10:35:39.709424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21845v3","created_at":"2026-07-05T10:35:39.709424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21845","created_at":"2026-07-05T10:35:39.709424+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7K3K5ZMSZSA","created_at":"2026-07-05T10:35:39.709424+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7K3K5ZMSZSA6H5L","created_at":"2026-07-05T10:35:39.709424+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7K3K5ZM","created_at":"2026-07-05T10:35:39.709424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09009","citing_title":"Scaling by Diversified Experience for Vision-Language-Action Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07383","citing_title":"RhinoVLA Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07383","citing_title":"RhinoVLA Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25477","citing_title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10070","citing_title":"AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18719","citing_title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08713","citing_title":"REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24182","citing_title":"$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23073","citing_title":"RL Token: Bootstrapping Online RL with Vision-Language-Action Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22551","citing_title":"QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ","json":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ.json","graph_json":"https://pith.science/api/pith-number/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/graph.json","events_json":"https://pith.science/api/pith-number/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/events.json","paper":"https://pith.science/paper/Q7K3K5ZM"},"agent_actions":{"view_html":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ","download_json":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ.json","view_paper":"https://pith.science/paper/Q7K3K5ZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21845&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/action/storage_attestation","attest_author":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/action/author_attestation","sign_citation":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/action/citation_signature","submit_replication":"https://pith.science/pith/Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ/action/replication_record"}},"created_at":"2026-07-05T10:35:39.709424+00:00","updated_at":"2026-07-05T10:35:39.709424+00:00"}