{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XIGQ6FYYDAQUPEVGNZU5WRG36O","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":"8ca863636708afadb1892f7be1e53f9b1e8e151372dcf474a728cb3f63543636","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T02:25:13Z","title_canon_sha256":"a8a5d659cba4877b290e272d23244147055578dfda63b047680a4e72f5859700"},"schema_version":"1.0","source":{"id":"2505.23003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23003","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23003v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23003","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"XIGQ6FYYDAQU","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"XIGQ6FYYDAQUPEVG","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"XIGQ6FYY","created_at":"2026-07-05T11:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:845e6fde5fc874c57de584f7ce28cf0f4b3910ed9c84d051941679cec90287d7","target":"graph","created_at":"2026-07-05T11:11:53Z","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/2505.23003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust reinforcement learning (RL) aims to learn policies that remain effective despite uncertainties in its environment, which frequently arise in real-world applications due to variations in environment dynamics. The robust RL methods learn a robust policy by maximizing value under the worst-case models within a predefined uncertainty set. Offline robust RL algorithms are particularly promising in scenarios where only a fixed dataset is available and new data cannot be collected. However, these approaches often require extensive offline data, and gathering such datasets for specific tasks in","authors_text":"Hung Le, Hung The Tran, Linh Le Pham Van, Minh Hoang Nguyen, Sunil Gupta","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T02:25:13Z","title":"Hybrid Cross-domain Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23003","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:e964d1f115ca06c831aa6f189ddce456a0cb52fff795145203b2bd520ceac986","target":"record","created_at":"2026-07-05T11:11:53Z","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":"8ca863636708afadb1892f7be1e53f9b1e8e151372dcf474a728cb3f63543636","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T02:25:13Z","title_canon_sha256":"a8a5d659cba4877b290e272d23244147055578dfda63b047680a4e72f5859700"},"schema_version":"1.0","source":{"id":"2505.23003","kind":"arxiv","version":1}},"canonical_sha256":"ba0d0f171818214792a66e69db44dbf3a4155ccb3827af27b282c493cd70e08b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0d0f171818214792a66e69db44dbf3a4155ccb3827af27b282c493cd70e08b","first_computed_at":"2026-07-05T11:11:53.304721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:53.304721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JqQT6TyVxs2UzRXjewSnI8PjHniRh/Luz0n//oPaYZVuWgsYZYl/QjvIzWakrIQH800ueAmk2+UWTcr9rgfoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:53.305201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e964d1f115ca06c831aa6f189ddce456a0cb52fff795145203b2bd520ceac986","sha256:845e6fde5fc874c57de584f7ce28cf0f4b3910ed9c84d051941679cec90287d7"],"state_sha256":"76f02fda5ec593c2b19355dc96901da722936ac6f5324fa792a46c4fb5eaebce"}