{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N7YNHNPWXX3OQ7GU2O7GQIFWP3","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":"7845c46fcb7790dcc7f83aed816a8d9053ff4794ad8f95e2b442012608738db7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-25T23:53:09Z","title_canon_sha256":"3cd525bcb3f4c239425eb15804895a7235e8b8a0751697d3099a941e51b597fd"},"schema_version":"1.0","source":{"id":"2606.27610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27610","created_at":"2026-06-29T00:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27610v1","created_at":"2026-06-29T00:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27610","created_at":"2026-06-29T00:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"N7YNHNPWXX3O","created_at":"2026-06-29T00:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"N7YNHNPWXX3OQ7GU","created_at":"2026-06-29T00:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"N7YNHNPW","created_at":"2026-06-29T00:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:1789c8e384204da2de2f65b80ea466d7d7b0d0ceeca091d35cfae0faa96b21a4","target":"graph","created_at":"2026-06-29T00:14:11Z","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/2606.27610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study finite-horizon Markov Decision Processes (MDPs) under distributional uncertainty in the transition kernels and develop a policy-gradient framework for Wasserstein distributionally robust control. Ambiguity is modeled by state-action dependent Wasserstein balls around nominal transition kernels, leading to a max-min control problem over randomized policies and admissible transition laws. Since the worst-case transition law depends implicitly on the policy parameters, the usual policy-gradient argument does not apply. We address this difficulty by using a Wasserstein dual reformulation ","authors_text":"Huy\\^en Pham, Kaixin Yan, Samy Mekkaoui, Yadh Hafsi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-25T23:53:09Z","title":"Policy Gradient Learning for Distributionally Robust Markov Decision Processes under Wasserstein Ambiguity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27610","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":"sha256:8d5a61aa8c814d5716e10db679b6e058576cc58294da2f09572187b6d0350cbd","target":"record","created_at":"2026-06-29T00:14:11Z","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":"7845c46fcb7790dcc7f83aed816a8d9053ff4794ad8f95e2b442012608738db7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-25T23:53:09Z","title_canon_sha256":"3cd525bcb3f4c239425eb15804895a7235e8b8a0751697d3099a941e51b597fd"},"schema_version":"1.0","source":{"id":"2606.27610","kind":"arxiv","version":1}},"canonical_sha256":"6ff0d3b5f6bdf6e87cd4d3be6820b67eeb0ec9b37b8637a48d42e3454ca7a165","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ff0d3b5f6bdf6e87cd4d3be6820b67eeb0ec9b37b8637a48d42e3454ca7a165","first_computed_at":"2026-06-29T00:14:11.693826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T00:14:11.693826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLuarrv6NoZuAzZB8uVmJUsdZA0KXXZEVtacaQ+x625QCnjO/gQeKokT1b0iL7C/nzswOLlkb9XnnRjWspLQBQ==","signature_status":"signed_v1","signed_at":"2026-06-29T00:14:11.694242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d5a61aa8c814d5716e10db679b6e058576cc58294da2f09572187b6d0350cbd","sha256:1789c8e384204da2de2f65b80ea466d7d7b0d0ceeca091d35cfae0faa96b21a4"],"state_sha256":"2f4259bc53c802cc74686bba76bbbf0c09fffcdebcca69dc3f7cef6e52842e46"}