{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7A255E3524FJZIHBY4L76BMEWW","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":"63bbb1cf9f81c5321c1b3f28f03f9f109c64b25a9d74d06bb9e9753dbadbe243","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T17:48:42Z","title_canon_sha256":"4aa2e3e500a23ca8df08db37931c4f9dbf49da053c69f904bc5993eec17f18db"},"schema_version":"1.0","source":{"id":"2403.12946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12946","created_at":"2026-07-05T08:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12946v2","created_at":"2026-07-05T08:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12946","created_at":"2026-07-05T08:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"7A255E3524FJ","created_at":"2026-07-05T08:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"7A255E3524FJZIHB","created_at":"2026-07-05T08:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"7A255E35","created_at":"2026-07-05T08:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:e67d83768d9ac05998071f9b478169f6f92f07b6019937efd46b5302735e5e05","target":"graph","created_at":"2026-07-05T08:37:18Z","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/2403.12946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL), the absence of active exploration calls for attention on the model robustness to tackle the sim-to-real gap, where the discrepancy between the simulated and deployed environments can significantly undermine the performance of the learned policy. To endow the learned policy with robustness in a sample-efficient manner in the presence of high-dimensional state-action space, this paper considers the sample complexity of distributionally robust linear Markov decision processes (MDPs) with an uncertainty set characterized by the total variation distance using","authors_text":"He Wang, Laixi Shi, Yuejie Chi","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T17:48:42Z","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12946","kind":"arxiv","version":2},"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":"sha256:24b9aa9ceb174d2127657ff6a705dd99956d1b45ed62fd55c8380fe4b40fef72","target":"record","created_at":"2026-07-05T08:37:18Z","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":"63bbb1cf9f81c5321c1b3f28f03f9f109c64b25a9d74d06bb9e9753dbadbe243","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T17:48:42Z","title_canon_sha256":"4aa2e3e500a23ca8df08db37931c4f9dbf49da053c69f904bc5993eec17f18db"},"schema_version":"1.0","source":{"id":"2403.12946","kind":"arxiv","version":2}},"canonical_sha256":"f835de937dd70a9ca0e1c717ff0584b594c889509515b57fbf64671812de853b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f835de937dd70a9ca0e1c717ff0584b594c889509515b57fbf64671812de853b","first_computed_at":"2026-07-05T08:37:18.847186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:18.847186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1RpPUTUojGZrRrLrh0crOq68HQS1aHmFQIuuEABcjHF8G0rfeSoVSemZ2adMjkdqc3qZ4DvIj0YYo88SmlTGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:18.847725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24b9aa9ceb174d2127657ff6a705dd99956d1b45ed62fd55c8380fe4b40fef72","sha256:e67d83768d9ac05998071f9b478169f6f92f07b6019937efd46b5302735e5e05"],"state_sha256":"d4aff097255e7dc884c2f3db88ed1e776da67e040fd671c1e5c92c619d69e741"}