{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XYDGOYHYDGSTONO5MOID5RCRPQ","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":"5906d02392c7c54537a091eaee7f64a57bc6477e63d29899720b271b3bb95f62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T15:46:27Z","title_canon_sha256":"a61aa3fb6328845f77aa519d0b7f33294e498d066059ddbd328e0bc5450d4e0e"},"schema_version":"1.0","source":{"id":"2605.14982","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14982","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14982v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14982","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"XYDGOYHYDGST","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XYDGOYHYDGSTONO5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XYDGOYHY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b419cd5d8a1db574c25d3b42d72188bfb3223c9724eeecc032e03c3737b818ae","target":"graph","created_at":"2026-05-17T23:38:55Z","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"},"paper":{"abstract_excerpt":"We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points under suitable assumptions. However, these methods rely on first-order updates. In contrast, second-order optimization provides principled curvature-aware updates that are proven to accelerate convergence, but its application in RL is limited by the computational complexity of Hessian estimation. In this work, we analyze second-order approximations for the ac","authors_text":"Sanjeev Manivannan, Shuban V","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T15:46:27Z","title":"Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14982","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":"sha256:286ab637e3a176ad5b2abf592fe3c7fc531e0a6a87c7429d21394879cdca170b","target":"record","created_at":"2026-05-17T23:38:55Z","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":"5906d02392c7c54537a091eaee7f64a57bc6477e63d29899720b271b3bb95f62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T15:46:27Z","title_canon_sha256":"a61aa3fb6328845f77aa519d0b7f33294e498d066059ddbd328e0bc5450d4e0e"},"schema_version":"1.0","source":{"id":"2605.14982","kind":"arxiv","version":1}},"canonical_sha256":"be066760f819a53735dd63903ec4517c15f37c0abb0dd3d0ed1637161b997d80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be066760f819a53735dd63903ec4517c15f37c0abb0dd3d0ed1637161b997d80","first_computed_at":"2026-05-17T23:38:55.101395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:55.101395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"74pNmLFna4g/ILZNCBPtNm7Ivj+xxqLNsGTqA07+7qzWpR5OAp0faDaZub4ciYfhpUBji+A6IJ1OVHyIR+AiBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:55.101995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14982","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:286ab637e3a176ad5b2abf592fe3c7fc531e0a6a87c7429d21394879cdca170b","sha256:b419cd5d8a1db574c25d3b42d72188bfb3223c9724eeecc032e03c3737b818ae"],"state_sha256":"a67eb4133b01e5a726068ccd1a15ff07ceb48648195454d4944f0e2acb5421ae"}