{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2EB2M2PKPNWUF262MWGHTJRP7Y","short_pith_number":"pith:2EB2M2PK","canonical_record":{"source":{"id":"2502.02265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T12:26:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae2430ad1f7cf84b6c2af9dfe4a2d0eb4d86b0bf3facaff088353069996ce509","abstract_canon_sha256":"519d6396c29d44a4a715953b5cb3dd8ee770f2652c12fa696ace116883c654e1"},"schema_version":"1.0"},"canonical_sha256":"d103a669ea7b6d42ebda658c79a62ffe1a3684b06a65df18a86242ae065d11df","source":{"kind":"arxiv","id":"2502.02265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02265","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02265v1","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02265","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"2EB2M2PKPNWU","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"2EB2M2PKPNWUF262","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"2EB2M2PK","created_at":"2026-07-05T10:09:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2EB2M2PKPNWUF262MWGHTJRP7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T12:26:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae2430ad1f7cf84b6c2af9dfe4a2d0eb4d86b0bf3facaff088353069996ce509","abstract_canon_sha256":"519d6396c29d44a4a715953b5cb3dd8ee770f2652c12fa696ace116883c654e1"},"schema_version":"1.0"},"canonical_sha256":"d103a669ea7b6d42ebda658c79a62ffe1a3684b06a65df18a86242ae065d11df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:26.259851Z","signature_b64":"LBQ464E+EP33eKrXLCp6vsxiIq6aywoDkzv7SBF38FAgqDsAlmHOgMeg4n6o4iXvCb9FYVcw2Jp36dhhxoWyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d103a669ea7b6d42ebda658c79a62ffe1a3684b06a65df18a86242ae065d11df","last_reissued_at":"2026-07-05T10:09:26.259432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:26.259432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02265","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D4/xMlG0SzpBdGBV1RMnIG+8UQ24bk9bTrYYuU7kH+LCzQwgfsPjEIUHjudqppjA4Wyn79K2iWweoOUeGSjOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:22:05.166958Z"},"content_sha256":"7cf8989caa948c908601175101b33e85b26db791da53c1fcae31a382a3e149e5","schema_version":"1.0","event_id":"sha256:7cf8989caa948c908601175101b33e85b26db791da53c1fcae31a382a3e149e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2EB2M2PKPNWUF262MWGHTJRP7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoran Qu, Donghe Chen, Han Wang, Lin Cheng, Tengjie Zheng, Yubin Peng","submitted_at":"2025-02-04T12:26:47Z","abstract_excerpt":"High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These issues are exacerbated when the task requires the agent to achieve a precise goal state, as is common in robotics and other real-world applications.We introduce Adviser-Actor-Critic (AAC), designed to address the precision control dilemma by combining the precision of feedback control theory with the adaptive learning capability of RL and featuring an Adviser th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02265","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/2502.02265/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WifuahGAZ0sH5WuTq8RbDVTsct/wLNdvknsndyU2FrlmtehVU1vzI9MXM79O+tyXiVoKeSMtWOnTX6WjX9YZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:22:05.167848Z"},"content_sha256":"9ef7fdc5ba8ea492b3ae086fa1cf218993dcd5b654c7602c91ff134747f0697d","schema_version":"1.0","event_id":"sha256:9ef7fdc5ba8ea492b3ae086fa1cf218993dcd5b654c7602c91ff134747f0697d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/bundle.json","state_url":"https://pith.science/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T12:22:05Z","links":{"resolver":"https://pith.science/pith/2EB2M2PKPNWUF262MWGHTJRP7Y","bundle":"https://pith.science/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/bundle.json","state":"https://pith.science/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2EB2M2PKPNWUF262MWGHTJRP7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2EB2M2PKPNWUF262MWGHTJRP7Y","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":"519d6396c29d44a4a715953b5cb3dd8ee770f2652c12fa696ace116883c654e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T12:26:47Z","title_canon_sha256":"ae2430ad1f7cf84b6c2af9dfe4a2d0eb4d86b0bf3facaff088353069996ce509"},"schema_version":"1.0","source":{"id":"2502.02265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02265","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02265v1","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02265","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"2EB2M2PKPNWU","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"2EB2M2PKPNWUF262","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"2EB2M2PK","created_at":"2026-07-05T10:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:9ef7fdc5ba8ea492b3ae086fa1cf218993dcd5b654c7602c91ff134747f0697d","target":"graph","created_at":"2026-07-05T10:09:26Z","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/2502.02265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These issues are exacerbated when the task requires the agent to achieve a precise goal state, as is common in robotics and other real-world applications.We introduce Adviser-Actor-Critic (AAC), designed to address the precision control dilemma by combining the precision of feedback control theory with the adaptive learning capability of RL and featuring an Adviser th","authors_text":"Chaoran Qu, Donghe Chen, Han Wang, Lin Cheng, Tengjie Zheng, Yubin Peng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T12:26:47Z","title":"Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02265","kind":"arxiv","version":1},"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":"sha256:7cf8989caa948c908601175101b33e85b26db791da53c1fcae31a382a3e149e5","target":"record","created_at":"2026-07-05T10:09:26Z","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":"519d6396c29d44a4a715953b5cb3dd8ee770f2652c12fa696ace116883c654e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T12:26:47Z","title_canon_sha256":"ae2430ad1f7cf84b6c2af9dfe4a2d0eb4d86b0bf3facaff088353069996ce509"},"schema_version":"1.0","source":{"id":"2502.02265","kind":"arxiv","version":1}},"canonical_sha256":"d103a669ea7b6d42ebda658c79a62ffe1a3684b06a65df18a86242ae065d11df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d103a669ea7b6d42ebda658c79a62ffe1a3684b06a65df18a86242ae065d11df","first_computed_at":"2026-07-05T10:09:26.259432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:26.259432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LBQ464E+EP33eKrXLCp6vsxiIq6aywoDkzv7SBF38FAgqDsAlmHOgMeg4n6o4iXvCb9FYVcw2Jp36dhhxoWyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:26.259851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cf8989caa948c908601175101b33e85b26db791da53c1fcae31a382a3e149e5","sha256:9ef7fdc5ba8ea492b3ae086fa1cf218993dcd5b654c7602c91ff134747f0697d"],"state_sha256":"6f8c29cbebc913ae99b84905aba51aced556eea02a1e4a908d0c4653e415bfe5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzbDGe+o5bOM5f7D+vFWBkoqmwXCQW9cId7vm8DanoalXrT6rnrRQtJ5v1meHukyBQUHLKCdT5klmxqimCpVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:22:05.175267Z","bundle_sha256":"014a03567a794617891ec1746c9ebe3b842012918d7f858d93c3d85b475b445e"}}