{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GL3EF2IV45LVMQWL5U6CMGKYXV","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":"6153cf3783f89e32940608f16a74e9e2f00c66991b02489900ad682949a97e9d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T17:42:59Z","title_canon_sha256":"6e4a94f878906b1089ffa366bbb1f490af81a730c146c75626a7d34f357a01a9"},"schema_version":"1.0","source":{"id":"2605.26078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26078","created_at":"2026-05-26T02:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26078v1","created_at":"2026-05-26T02:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26078","created_at":"2026-05-26T02:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"GL3EF2IV45LV","created_at":"2026-05-26T02:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"GL3EF2IV45LVMQWL","created_at":"2026-05-26T02:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"GL3EF2IV","created_at":"2026-05-26T02:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:002a0a13761990a5529f30456d47516b368fc2d130b21e1bd1511aef09477a4e","target":"graph","created_at":"2026-05-26T02:05:26Z","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/2605.26078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions. For the entropy-regularized RL objective, WPG evolves each state-conditional policy by transporting it along the action gradient of the soft Q-function together with a Langevin-type diffusion. Despite its appeal for continuous-control problems, its global convergence properties remain poorly understood. Standard Langevin analyses do not directly apply, because the RL objective depends on the policy through the Bellman recursion ","authors_text":"Rui Gao, Shuang Li, Zhaoyu Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T17:42:59Z","title":"Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26078","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":"sha256:8cd0f96ee81741d6bad2770a35edd4f4ef2d9bbf0dba2286fee7d9489ceb2b89","target":"record","created_at":"2026-05-26T02:05:26Z","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":"6153cf3783f89e32940608f16a74e9e2f00c66991b02489900ad682949a97e9d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T17:42:59Z","title_canon_sha256":"6e4a94f878906b1089ffa366bbb1f490af81a730c146c75626a7d34f357a01a9"},"schema_version":"1.0","source":{"id":"2605.26078","kind":"arxiv","version":1}},"canonical_sha256":"32f642e915e7575642cbed3c261958bd678e1bba51cdfd7d34acefb8085e582b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32f642e915e7575642cbed3c261958bd678e1bba51cdfd7d34acefb8085e582b","first_computed_at":"2026-05-26T02:05:26.146613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:26.146613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rj80WvvWF/U/uAy5+jjz8RrJDNfnhvI7c6iUFVO8RjDfV8DZTFRlJCe1hj34j4MvqNL5cXLTnAnzrbJR6e6rCA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:26.147233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cd0f96ee81741d6bad2770a35edd4f4ef2d9bbf0dba2286fee7d9489ceb2b89","sha256:002a0a13761990a5529f30456d47516b368fc2d130b21e1bd1511aef09477a4e"],"state_sha256":"4bf6e17ad7d93c6f198da95fd5c6fdb68a367edb212687cd85b40c3a8ed280df"}