{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LVVGDS222TNEUSBJWFLXQODPBK","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":"9e99c036f6a425101488931bfd3aee97a0a990b05abbabee3be8b008c4e1cd14","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T03:04:53Z","title_canon_sha256":"fa46760567190a27c91ff7185c9cb0f0bea9e3ce5ca1fe8bc5dc786081b1a37b"},"schema_version":"1.0","source":{"id":"2502.00288","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00288","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00288v2","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00288","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"LVVGDS222TNE","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"LVVGDS222TNEUSBJ","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"LVVGDS22","created_at":"2026-07-05T11:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:6ab35dff8c478f94ffc866dc749b1f957ae4b48edec5c194ff61df212ac5402e","target":"graph","created_at":"2026-07-05T11:11:40Z","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/2502.00288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to \"kick-start\" training, achieving promising results in continuous control. However, they typically compute the Q-function independently for each action dimension, neglecting interdependencies and making it harder to identify optimal actions when learning from suboptimal data, such as non-expert demonstr","authors_text":"Chao Yu, Feng Gao, Jijia Liu, Qingmin Liao, Yu Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T03:04:53Z","title":"Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00288","kind":"arxiv","version":2},"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:bee160e4b0432209cd4da3caea2bbbe5d1e5a813e77b1b43441001db8a0606fa","target":"record","created_at":"2026-07-05T11:11:40Z","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":"9e99c036f6a425101488931bfd3aee97a0a990b05abbabee3be8b008c4e1cd14","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T03:04:53Z","title_canon_sha256":"fa46760567190a27c91ff7185c9cb0f0bea9e3ce5ca1fe8bc5dc786081b1a37b"},"schema_version":"1.0","source":{"id":"2502.00288","kind":"arxiv","version":2}},"canonical_sha256":"5d6a61cb5ad4da4a4829b15778386f0a8d8523ada94c38f1169dc83db410742e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d6a61cb5ad4da4a4829b15778386f0a8d8523ada94c38f1169dc83db410742e","first_computed_at":"2026-07-05T11:11:40.321471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:40.321471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pw1TUWveWZevmUPPt1knP363N5QLpiM7bUMY7Y7nhxUPFD8IKQMJ09vT/+yA3eWlpn/EJQKvQOscFAvB7xLDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:40.321977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00288","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bee160e4b0432209cd4da3caea2bbbe5d1e5a813e77b1b43441001db8a0606fa","sha256:6ab35dff8c478f94ffc866dc749b1f957ae4b48edec5c194ff61df212ac5402e"],"state_sha256":"3e908e1147138b580587fbaaa7cdd1281d493503db3638200411f53ec2a9f1c4"}