{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LURVJ6B73RBEAS2URTSVMKEDIV","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":"48a7e2fd2034c11ab2c66becc3162e8796a84ceb3abd13fd32f87c2786d9c990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T08:20:02Z","title_canon_sha256":"b349fc0f950ec047c055f062380c30b275780bb1af629d77f8517c37210d4b8b"},"schema_version":"1.0","source":{"id":"2608.10634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10634","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10634v1","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10634","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"LURVJ6B73RBE","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"LURVJ6B73RBEAS2U","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"LURVJ6B7","created_at":"2026-08-12T01:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:49bf0527ded7a90a187cf1866968907a2e572158698130630341beccf3167aab","target":"graph","created_at":"2026-08-12T01:22:54Z","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/2608.10634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making. Numerous methods have been developed to improve dynamics prediction and policy optimization for MBRL through uncertainty estimation, model regularization, and conservative value learning. However, these methods typically treat the transition model and critic as monolithic predictors, overlooking the policy-induced data bias. Consequently, action can become entangled with environmental evolution, while uneven action coverage ","authors_text":"Jie Qiao, Ruichu Cai, Weilin Chen, Zefeng Liang, Zhifeng Hao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T08:20:02Z","title":"IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10634","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:fec4835f9bdfe6fcf5d2f0113dbae09912edbcfce68284589ad07c141f14c5f0","target":"record","created_at":"2026-08-12T01:22:54Z","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":"48a7e2fd2034c11ab2c66becc3162e8796a84ceb3abd13fd32f87c2786d9c990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T08:20:02Z","title_canon_sha256":"b349fc0f950ec047c055f062380c30b275780bb1af629d77f8517c37210d4b8b"},"schema_version":"1.0","source":{"id":"2608.10634","kind":"arxiv","version":1}},"canonical_sha256":"5d2354f83fdc42404b548ce5562883456937bc1ebf1b6716509a64c70a8a4712","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d2354f83fdc42404b548ce5562883456937bc1ebf1b6716509a64c70a8a4712","first_computed_at":"2026-08-12T01:22:54.906994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:54.906994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yg3S/OdHULAPE/leCfp0Otxn7KErm97VsQ4KQm7PA/CbPNH329Lmu+ABtBR60rWKpta6/hgZaz6pz0J5pw9hDA==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:54.908629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fec4835f9bdfe6fcf5d2f0113dbae09912edbcfce68284589ad07c141f14c5f0","sha256:49bf0527ded7a90a187cf1866968907a2e572158698130630341beccf3167aab"],"state_sha256":"9fe160b4abb4b9a7fa0f25abf7d0dda3a1361d4909de5bac1bd006af35e9f3ce"}