{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LGMCAM66SLSVI3OPCF4ZH5DP5Q","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":"aeea7efdbb2b9b8dea95bc1ce4b36157d8151647c3fe62a95fd27b5774eed339","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T19:08:42Z","title_canon_sha256":"e29afd7431953d8df671383ad1b98fddeabecbf47b1bea97a1b80d9b6b001af7"},"schema_version":"1.0","source":{"id":"2502.03550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03550","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03550v1","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03550","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"LGMCAM66SLSV","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"LGMCAM66SLSVI3OP","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"LGMCAM66","created_at":"2026-07-05T10:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:734d2ba3bdc85b08d6aec11c91b07938c1bc33916f7166263b70a5eae6665766","target":"graph","created_at":"2026-07-05T10:10:11Z","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/2502.03550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we discover that existing methods that rely on standard SAC-style policy iteration for value learning, directly using data generated by the planner, often result in \\emph{persistent value overestimation}. Through theoretical analysis and experiments, we argue that this issue is deeply rooted in the structural policy mismatch between the data generation policy tha","authors_text":"Guanya Shi, Haotian Lin, Jeff Schneider, Pengcheng Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T19:08:42Z","title":"TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03550","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":"sha256:4bfd28333dfed9ee820561c6ada1914402d2fb8606ec67f9f14c1c92f6d4e60a","target":"record","created_at":"2026-07-05T10:10:11Z","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":"aeea7efdbb2b9b8dea95bc1ce4b36157d8151647c3fe62a95fd27b5774eed339","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T19:08:42Z","title_canon_sha256":"e29afd7431953d8df671383ad1b98fddeabecbf47b1bea97a1b80d9b6b001af7"},"schema_version":"1.0","source":{"id":"2502.03550","kind":"arxiv","version":1}},"canonical_sha256":"59982033de92e5546dcf117993f46fec38401888a271ee375fb72833d263522a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59982033de92e5546dcf117993f46fec38401888a271ee375fb72833d263522a","first_computed_at":"2026-07-05T10:10:11.937051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:11.937051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EOPurSGBC0eyAsGY7EtwTP+8LfB9EEaLMamuXFfwzj8eLj0ULvknldnxOzQ+f19KudNQBR2+M+5QtoNgGVV9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:11.937535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bfd28333dfed9ee820561c6ada1914402d2fb8606ec67f9f14c1c92f6d4e60a","sha256:734d2ba3bdc85b08d6aec11c91b07938c1bc33916f7166263b70a5eae6665766"],"state_sha256":"85c0732a0dad0732352385aad6b30d5736dfa9df6ea36222b07cd041209ae253"}