{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q7K3K5ZMSZSA6H5LJ4TMF2LOVJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d2e6db4b97cde8ae5a12ec150790c112220fb3fee7758abc845ff73e0cf394d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T08:12:20Z","title_canon_sha256":"87d72f64e9ac3cd3b2641100904a073db3d82783813c744f2040d8f7ba04b07f"},"schema_version":"1.0","source":{"id":"2410.21845","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21845","created_at":"2026-07-05T10:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21845v3","created_at":"2026-07-05T10:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21845","created_at":"2026-07-05T10:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q7K3K5ZMSZSA","created_at":"2026-07-05T10:35:39Z"},{"alias_kind":"pith_short_16","alias_value":"Q7K3K5ZMSZSA6H5L","created_at":"2026-07-05T10:35:39Z"},{"alias_kind":"pith_short_8","alias_value":"Q7K3K5ZM","created_at":"2026-07-05T10:35:39Z"}],"graph_snapshots":[{"event_id":"sha256:b046a737e3f5fdf9c8dc56f8cfbaa87ce3b62b8598e886416a4d4a3b06a17cbc","target":"graph","created_at":"2026-07-05T10:35:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.21845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charles Xu, Jeffrey Wu, Jianlan Luo, Sergey Levine","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T08:12:20Z","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21845","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e1ac2d6be1e9e4adba1fda85afb055c0558dba12b3aa6798e2fee8b2937f5ba","target":"record","created_at":"2026-07-05T10:35:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d2e6db4b97cde8ae5a12ec150790c112220fb3fee7758abc845ff73e0cf394d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T08:12:20Z","title_canon_sha256":"87d72f64e9ac3cd3b2641100904a073db3d82783813c744f2040d8f7ba04b07f"},"schema_version":"1.0","source":{"id":"2410.21845","kind":"arxiv","version":3}},"canonical_sha256":"87d5b5772c96640f1fab4f26c2e96eaa6cf124962a1995fb1196b1d65c082e64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87d5b5772c96640f1fab4f26c2e96eaa6cf124962a1995fb1196b1d65c082e64","first_computed_at":"2026-07-05T10:35:39.709364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:39.709364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//mtde81LqYDXNAcOf+jKKyfE0gUqPx9esH1x3pVbdFap8tFGlv429gzap4tnANqno6f4mrVCn0XM9KYfL1gBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:39.709882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21845","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1ac2d6be1e9e4adba1fda85afb055c0558dba12b3aa6798e2fee8b2937f5ba","sha256:b046a737e3f5fdf9c8dc56f8cfbaa87ce3b62b8598e886416a4d4a3b06a17cbc"],"state_sha256":"6658426153788472040bc428c1b3ceff02c63e02d1d2f2064d1714f86ffcc6d2"}