{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VOI3K5KN5PJYBI42VRLLOP2IFR","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":"c9e2e3f76ce055ab78d84e34c7e7cbd16bf095160cf147d79275dd84ffa62c54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T19:29:09Z","title_canon_sha256":"98594d282672c8ca7f242e85b31a5aaf62a67c61fb9d50abd4447d0c92a7207e"},"schema_version":"1.0","source":{"id":"2404.05055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05055","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05055v1","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05055","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"VOI3K5KN5PJY","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"VOI3K5KN5PJYBI42","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"VOI3K5KN","created_at":"2026-07-05T08:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:53bc9d3617d6976817bc91c4d7ab424eeef7a52f4fa5055c5bd5aaaaa26474e4","target":"graph","created_at":"2026-07-05T08:05:25Z","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/2404.05055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the \\emph{percentile criterion}. The percentile criterion is approximately solved by constructing an \\emph{ambiguity set} that contains the true model with high probability and optimizing the policy for the worst model in the set. Since the percentile criterion is non-convex, constructing ambiguity sets is often challenging. Existing work uses \\emph{Bayesian credible regions} as ambiguity sets, but they are often unnecessarily large and result in learning ove","authors_text":"Cyrus Cousins, Elita A. Lobo, Marek Petrik, Yair Zick","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T19:29:09Z","title":"Percentile Criterion Optimization in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05055","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:dde590c1bb0cd9e4f8893fd1703d54f53d8201c407e2b87dd404adb86ba59287","target":"record","created_at":"2026-07-05T08:05:25Z","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":"c9e2e3f76ce055ab78d84e34c7e7cbd16bf095160cf147d79275dd84ffa62c54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T19:29:09Z","title_canon_sha256":"98594d282672c8ca7f242e85b31a5aaf62a67c61fb9d50abd4447d0c92a7207e"},"schema_version":"1.0","source":{"id":"2404.05055","kind":"arxiv","version":1}},"canonical_sha256":"ab91b5754debd380a39aac56b73f482c5def125e9de132772ed50d885fe6116b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab91b5754debd380a39aac56b73f482c5def125e9de132772ed50d885fe6116b","first_computed_at":"2026-07-05T08:05:25.452422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:25.452422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c6mDyZoGr1OcmFC42C7tKdaEbhOcVl8zPzKAom0Lv7ROs5DBpZ96BpHTo06gsdj+rq8z59ULYzf3XlZrPP6GBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:25.453038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dde590c1bb0cd9e4f8893fd1703d54f53d8201c407e2b87dd404adb86ba59287","sha256:53bc9d3617d6976817bc91c4d7ab424eeef7a52f4fa5055c5bd5aaaaa26474e4"],"state_sha256":"c6d932dd9daf68a6c89284a51e4371c95773374221b8a211d3b6694822a8d6aa"}