{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PSYHHRSUXPT2EDMBFHHCDHUQLC","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":"2eb09ae68a96a5700b8ec7cfd1ebc3c04406bb50afe9e4cbe827fc8b78a5de89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:53:42Z","title_canon_sha256":"04934deeb4ad9ca71966ea4dd7fc84a2a264bb2ee2e667f2a039fd8601c10999"},"schema_version":"1.0","source":{"id":"2605.26784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26784","created_at":"2026-05-27T01:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26784v1","created_at":"2026-05-27T01:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26784","created_at":"2026-05-27T01:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"PSYHHRSUXPT2","created_at":"2026-05-27T01:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"PSYHHRSUXPT2EDMB","created_at":"2026-05-27T01:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"PSYHHRSU","created_at":"2026-05-27T01:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:066669580a131232b3a62362eae8b1876861b1e9ef73a696c0ba33aaa8089cb4","target":"graph","created_at":"2026-05-27T01:06:12Z","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/2605.26784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly constraining the policy ratio variance provides a principled local approximation to trust-region constraints, eliminating the need for binary hard clipping. By acting as a distributional ``soft brake'', this approach preserves critical gradient signals from novel discoveries while naturally down-weighting and enabling the reuse of stale, off-policy data. We","authors_text":"Dong Li, Fuchun Sun, Huaping Liu, Jianye Hao, Lei Lv, Shuo Han, Yihan Hu, Yu Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:53:42Z","title":"Ratio-Variance Regularized Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26784","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":"sha256:430e8e05601011a3badfad1ab7db32807fead181f43f5119483afb6bceb9c7fc","target":"record","created_at":"2026-05-27T01:06:12Z","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":"2eb09ae68a96a5700b8ec7cfd1ebc3c04406bb50afe9e4cbe827fc8b78a5de89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:53:42Z","title_canon_sha256":"04934deeb4ad9ca71966ea4dd7fc84a2a264bb2ee2e667f2a039fd8601c10999"},"schema_version":"1.0","source":{"id":"2605.26784","kind":"arxiv","version":1}},"canonical_sha256":"7cb073c654bbe7a20d8129ce219e905894f5d1a267d6d596c820d95cb3303d56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cb073c654bbe7a20d8129ce219e905894f5d1a267d6d596c820d95cb3303d56","first_computed_at":"2026-05-27T01:06:12.532841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:12.532841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UAzNUibJwklN1uhkUfCvgN7YY8VRtNWGXrMmuSP0yBPqtJbs4ANQKDKIvaGiXeAv4y2YRyBUNAsw+quqh2ZoDw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:12.533522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:430e8e05601011a3badfad1ab7db32807fead181f43f5119483afb6bceb9c7fc","sha256:066669580a131232b3a62362eae8b1876861b1e9ef73a696c0ba33aaa8089cb4"],"state_sha256":"46f8a3d077bbd8d2ff5d373c65ef2a7f0138fd0688328ad4dd379ca024eb5165"}