{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IPWRSR7LOYT5K7Y22YWGKDVABN","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":"b09850ecdc370cd82c1d358d6bfdbe37d1a984f3753236e8bbf2457d4be4856d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T12:32:52Z","title_canon_sha256":"0bd60d7c9ac6a87f7aa6ff7ba28e7167b0c97ad6914f36d49695970356d65313"},"schema_version":"1.0","source":{"id":"2506.01597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01597","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01597v1","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01597","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"IPWRSR7LOYT5","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"IPWRSR7LOYT5K7Y2","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"IPWRSR7L","created_at":"2026-07-05T11:14:16Z"}],"graph_snapshots":[{"event_id":"sha256:ff3fbe5c53e53cfba437da387206e81c1df5abf98c6e5d61b35cc74fa26f3c7d","target":"graph","created_at":"2026-07-05T11:14:16Z","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/2506.01597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods like Newton's method demonstrate faster convergence than first-order approaches, current RKHS-based policy optimization remains constrained to first-order techniques. This limitation stems primarily from the intractability of explicitly computing and inverting the infinite-dimensional Hessian operator in RKHS. We introduce Policy Newton in RKHS, the first second-order optimization framework specifically designed for R","authors_text":"Chao Wang, Huaze Tang, Wenbo Ding, Yixian Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T12:32:52Z","title":"Policy Newton Algorithm in Reproducing Kernel Hilbert Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01597","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:df66996f3ac561ebf250bfd2bb4be53c9ef813abf7938190842b729eb459c6f8","target":"record","created_at":"2026-07-05T11:14:16Z","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":"b09850ecdc370cd82c1d358d6bfdbe37d1a984f3753236e8bbf2457d4be4856d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T12:32:52Z","title_canon_sha256":"0bd60d7c9ac6a87f7aa6ff7ba28e7167b0c97ad6914f36d49695970356d65313"},"schema_version":"1.0","source":{"id":"2506.01597","kind":"arxiv","version":1}},"canonical_sha256":"43ed1947eb7627d57f1ad62c650ea00b790ccae6f647febfe16ffb533eff23f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43ed1947eb7627d57f1ad62c650ea00b790ccae6f647febfe16ffb533eff23f1","first_computed_at":"2026-07-05T11:14:16.459031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:16.459031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZRjBhKRA1nJDFX0ka2wUj7TkOH5xEGGKlp346+R22ZicPMMxtWtZ+SY6QYwbzA7EdV55Gs68hlPoEGD5XKdeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:16.459586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df66996f3ac561ebf250bfd2bb4be53c9ef813abf7938190842b729eb459c6f8","sha256:ff3fbe5c53e53cfba437da387206e81c1df5abf98c6e5d61b35cc74fa26f3c7d"],"state_sha256":"3baf013b3f6f2f4b7ab39ad69267fbc7c5c234258f0478ab7014c5bb15aa6c9d"}