{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VPOW74ZELNTEAOXGVOF5NUWPY7","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":"d7a496f595c4759edbe5457878c84c2321cdf2607d7f0f0262fa0dbde283578b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T11:49:33Z","title_canon_sha256":"ef803aae9f11aeec3d766e289d439ace17b01277550c2f355bdf12a91cae0784"},"schema_version":"1.0","source":{"id":"2309.02157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02157","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02157v1","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02157","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"VPOW74ZELNTE","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"VPOW74ZELNTEAOXG","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"VPOW74ZE","created_at":"2026-07-05T06:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:47ca3b844b99611862ce818eb21c7e1161727943aceab7692bd2c5a1c7656fed","target":"graph","created_at":"2026-07-05T06:47:49Z","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/2309.02157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based offline reinforcement learning (RL), which builds a supervised transition model with logging dataset to avoid costly interactions with the online environment, has been a promising approach for offline policy optimization. As the discrepancy between the logging data and online environment may result in a distributional shift problem, many prior works have studied how to build robust transition models conservatively and estimate the model uncertainty accurately. However, the over-conservatism can limit the exploration of the agent, and the uncertainty estimates may be unreliable. In ","authors_text":"Bolei Zhang, Junming Yang, Shengyuan Wang, Xingguo Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T11:49:33Z","title":"Model-based Offline Policy Optimization with Adversarial Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02157","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":"sha256:6229112e0b35b6088f7042ad2fd94077550309e1a0ebac93e995ec3d8fef6975","target":"record","created_at":"2026-07-05T06:47:49Z","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":"d7a496f595c4759edbe5457878c84c2321cdf2607d7f0f0262fa0dbde283578b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T11:49:33Z","title_canon_sha256":"ef803aae9f11aeec3d766e289d439ace17b01277550c2f355bdf12a91cae0784"},"schema_version":"1.0","source":{"id":"2309.02157","kind":"arxiv","version":1}},"canonical_sha256":"abdd6ff3245b66403ae6ab8bd6d2cfc7dc92859074bb8257589b9f2707ce365e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abdd6ff3245b66403ae6ab8bd6d2cfc7dc92859074bb8257589b9f2707ce365e","first_computed_at":"2026-07-05T06:47:49.281644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:49.281644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m8ANYrfjnNOuKBi9qudeU1bhmpS7KOpBLXLqX2o1BETMUSWwekP6HlyYOrmD8IfzgeEImrgjjdZsqXvlp78sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:49.282125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6229112e0b35b6088f7042ad2fd94077550309e1a0ebac93e995ec3d8fef6975","sha256:47ca3b844b99611862ce818eb21c7e1161727943aceab7692bd2c5a1c7656fed"],"state_sha256":"902f24b8148e20712df5188c5a58ce49c8b04430ec99a18a63ac98f82a0a79bd"}