{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DUU2F4QQDSFGQGTJ2OSJR55MBW","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":"0f75026b3a6de1bb66d00484e67c3054c4df4af5cfd903a7cb10e324ada2c82b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-30T11:38:13Z","title_canon_sha256":"98cf6fca8c27fedef244c5df872c33e77db755ab11f193d4d8b41d205c1729b6"},"schema_version":"1.0","source":{"id":"2310.00344","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00344","created_at":"2026-07-05T08:27:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00344v3","created_at":"2026-07-05T08:27:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00344","created_at":"2026-07-05T08:27:42Z"},{"alias_kind":"pith_short_12","alias_value":"DUU2F4QQDSFG","created_at":"2026-07-05T08:27:42Z"},{"alias_kind":"pith_short_16","alias_value":"DUU2F4QQDSFGQGTJ","created_at":"2026-07-05T08:27:42Z"},{"alias_kind":"pith_short_8","alias_value":"DUU2F4QQ","created_at":"2026-07-05T08:27:42Z"}],"graph_snapshots":[{"event_id":"sha256:23aa30b7e14cb0a52dad0df46409a04ac937ff7c191e6aefb9f533c66f9a7e76","target":"graph","created_at":"2026-07-05T08:27:42Z","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/2310.00344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling. In this paper, through a dedicated empirical investigation, we gain a deeper understanding of the role each task plays in world models and uncover the overlooked potential of sample-efficient MBRL by mitigating the domination of either observation or reward modeling. Our key insight is that while prevalent approaches of explicit MBRL attempt to res","authors_text":"Chenjun Xiao, Dong Li, Haoyu Ma, Jialong Wu, Jianmin Wang, Jianye Hao, Mingsheng Long, Ningya Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-30T11:38:13Z","title":"HarmonyDream: Task Harmonization Inside World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00344","kind":"arxiv","version":3},"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:d29b2e8c95acf4b7c18f2d20f0ac65b14f33f3229dc74ad9944b51d38f840188","target":"record","created_at":"2026-07-05T08:27:42Z","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":"0f75026b3a6de1bb66d00484e67c3054c4df4af5cfd903a7cb10e324ada2c82b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-30T11:38:13Z","title_canon_sha256":"98cf6fca8c27fedef244c5df872c33e77db755ab11f193d4d8b41d205c1729b6"},"schema_version":"1.0","source":{"id":"2310.00344","kind":"arxiv","version":3}},"canonical_sha256":"1d29a2f2101c8a681a69d3a498f7ac0d842f26b4855027d09dc776048dd26d11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d29a2f2101c8a681a69d3a498f7ac0d842f26b4855027d09dc776048dd26d11","first_computed_at":"2026-07-05T08:27:42.513226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:42.513226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PPXeOQ/gQqH7K69dM6SAF5KeUuflrwiAR2wMDUefDrvvnKmvCsVflbHgFebLEY+emO/RcdwzcoklemT2KFPqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:42.513773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00344","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d29b2e8c95acf4b7c18f2d20f0ac65b14f33f3229dc74ad9944b51d38f840188","sha256:23aa30b7e14cb0a52dad0df46409a04ac937ff7c191e6aefb9f533c66f9a7e76"],"state_sha256":"a5c3aff1ad728f2c964565fa2d9d6e43d0c4a1146bd36716d2df5f2d9931a752"}