{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QVMXLUAMBJTKRUXK533CMTRK7N","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":"f3abfad1e6ff37651d1e7e55ef92210f18bd233866385364701eba855b35fe5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T19:06:51Z","title_canon_sha256":"e9b959201aec43accc4cd73f679965a72aa37310c068be04673bd3bb18bba847"},"schema_version":"1.0","source":{"id":"2605.26282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26282","created_at":"2026-05-27T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26282v1","created_at":"2026-05-27T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26282","created_at":"2026-05-27T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"QVMXLUAMBJTK","created_at":"2026-05-27T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"QVMXLUAMBJTKRUXK","created_at":"2026-05-27T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"QVMXLUAM","created_at":"2026-05-27T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:c851decfe03a8c5aea09bfee437fb65658221352925f663ff0db5c3162158f32","target":"graph","created_at":"2026-05-27T01:05:09Z","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/2605.26282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and error compounding, which degrade long-horizon predictions. Beyond these issues, we identify a more critical yet underexplored bottleneck: a structural misalignment between search and value learning in existing world model approaches. In particular, policy improvement often relies on value functions induced by a separate, non-search policy, resulting in trainin","authors_text":"Che Liu, Hai Wang, Wenxuan Yuan, Xiaoyuan Cheng, Yiming Yang, Yuanzhao Zhang, Zhancun Mu, Zhuo Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T19:06:51Z","title":"Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26282","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":"sha256:65d7eace50a3e0613bd9ff6667ef7779cd68db45ccad11f1fd29a4aa4684f882","target":"record","created_at":"2026-05-27T01:05:09Z","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":"f3abfad1e6ff37651d1e7e55ef92210f18bd233866385364701eba855b35fe5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T19:06:51Z","title_canon_sha256":"e9b959201aec43accc4cd73f679965a72aa37310c068be04673bd3bb18bba847"},"schema_version":"1.0","source":{"id":"2605.26282","kind":"arxiv","version":1}},"canonical_sha256":"855975d00c0a66a8d2eaeef6264e2afb5bdd6c419b35e971d8e3ea9a5d3af337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"855975d00c0a66a8d2eaeef6264e2afb5bdd6c419b35e971d8e3ea9a5d3af337","first_computed_at":"2026-05-27T01:05:09.977574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:09.977574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QqnpPvN0TfRKueurcIFomrKJItFf+0edsztTks9D0iFivdBXbUbnAZk8heWgKyPbbChCKFAJDwvgreUNbAgoDA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:09.978418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65d7eace50a3e0613bd9ff6667ef7779cd68db45ccad11f1fd29a4aa4684f882","sha256:c851decfe03a8c5aea09bfee437fb65658221352925f663ff0db5c3162158f32"],"state_sha256":"02046b5207db8eba30770077579bc86a5a80d29de2874634ecd1f69e3d3cf239"}