{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C33AFYNRS7X2FNGROROZNUUKNS","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":"871483254df9c451c06829892c662c34cb122c8bfa2f53b80e13e5613ffcee0a","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T08:38:29Z","title_canon_sha256":"5f45e4b53d8c4eee0aff1ad5cc978869b45dae2130924c1f9248b28c3c5b9603"},"schema_version":"1.0","source":{"id":"2605.24939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24939","created_at":"2026-05-26T01:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24939v1","created_at":"2026-05-26T01:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24939","created_at":"2026-05-26T01:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"C33AFYNRS7X2","created_at":"2026-05-26T01:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"C33AFYNRS7X2FNGR","created_at":"2026-05-26T01:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"C33AFYNR","created_at":"2026-05-26T01:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:3764634bbffec134796134fdcadc9516eb68149eb7d6f9c674a683d88f908aa2","target":"graph","created_at":"2026-05-26T01:04:06Z","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/2605.24939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function approximation, which extend the tabular softmax parameterization while retaining a tractable policy class. Under $Q^\\pi_\\tau$-realizability for the regularized state-action value function, we first establish a non-uniform Polyak--{\\L}ojasiewicz (P\\L) inequality. The non-uniformity arises through degeneracy of constants associated with the policy geometry, namely the Fish","authors_text":"David \\v{S}i\\v{s}ka, Lukasz Szpruch, Ziyue Chen","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T08:38:29Z","title":"Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24939","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":"sha256:757d1fab6f4aba180ebb045b0abf538a4f06b3fe4271ba59ad0639781c66ffa9","target":"record","created_at":"2026-05-26T01:04:06Z","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":"871483254df9c451c06829892c662c34cb122c8bfa2f53b80e13e5613ffcee0a","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T08:38:29Z","title_canon_sha256":"5f45e4b53d8c4eee0aff1ad5cc978869b45dae2130924c1f9248b28c3c5b9603"},"schema_version":"1.0","source":{"id":"2605.24939","kind":"arxiv","version":1}},"canonical_sha256":"16f602e1b197efa2b4d1745d96d28a6ca0415da9aaf96eba26125e2ab68b0592","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16f602e1b197efa2b4d1745d96d28a6ca0415da9aaf96eba26125e2ab68b0592","first_computed_at":"2026-05-26T01:04:06.740223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:04:06.740223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YYACD2EW1ioWzcctETLwaUHLJK9nYkJH8YhekkUusHSjuRv2AdhCSaXt1L+7pm0uDp5JO6C1GYoYA1UWcJDoCw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:04:06.740971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:757d1fab6f4aba180ebb045b0abf538a4f06b3fe4271ba59ad0639781c66ffa9","sha256:3764634bbffec134796134fdcadc9516eb68149eb7d6f9c674a683d88f908aa2"],"state_sha256":"e163ba6e4f4746d902b1be8a2319a044f6fcacb68e76cad51f4080313bb2971f"}