{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KJW4776S5RZHZVRO2JPYGA2UV3","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":"686353101109378fbc7c47cb76324391b3d9fa11a997886ff90c2b5114481b0f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-02-01T22:05:48Z","title_canon_sha256":"44ad21add2c04ce090f744193bb691c34220ae700db90d15e3fc500a23f2a3f5"},"schema_version":"1.0","source":{"id":"2602.01460","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01460","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01460v3","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01460","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"KJW4776S5RZH","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"KJW4776S5RZHZVRO","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"KJW4776S","created_at":"2026-06-02T01:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:8a7bcdb60b29256e92452c6da0435df94f7cc50bdc73d42a44b1fa94886921cb","target":"graph","created_at":"2026-06-02T01:03:15Z","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/2602.01460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the noise-to-signal ratio (NSR) of a policy-gradient estimator, defined as the estimator variance (noise) normalized by the squared norm of the true gradient (signal). Our main result is that, for (i) finite-horizon linear systems with Gaussian policies and linear state-feedback, and (ii) finite-horizon polynomial systems with Gaussian policies and polynomial feedback, the NSR of the REINFORCE estimator can be characterize","authors_text":"Haoyu Han, Heng Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-02-01T22:05:48Z","title":"Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01460","kind":"arxiv","version":3},"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:e70d7043102b26de0089769d5cecb46c3cfebd4ada4fc8bebf347780675b0e18","target":"record","created_at":"2026-06-02T01:03:15Z","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":"686353101109378fbc7c47cb76324391b3d9fa11a997886ff90c2b5114481b0f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-02-01T22:05:48Z","title_canon_sha256":"44ad21add2c04ce090f744193bb691c34220ae700db90d15e3fc500a23f2a3f5"},"schema_version":"1.0","source":{"id":"2602.01460","kind":"arxiv","version":3}},"canonical_sha256":"526dcfffd2ec727cd62ed25f830354aee01f06e0177613bbf5c675d5181860b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526dcfffd2ec727cd62ed25f830354aee01f06e0177613bbf5c675d5181860b1","first_computed_at":"2026-06-02T01:03:15.568227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:15.568227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nnyo20JZ1OKnkVdNaQ6UrxWHbyPhICm+vm60jcbyMRqZ+G5fhKQFpnijXMwhiuYIlYBouxH3U5CltdrOUdFICA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:15.568780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01460","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e70d7043102b26de0089769d5cecb46c3cfebd4ada4fc8bebf347780675b0e18","sha256:8a7bcdb60b29256e92452c6da0435df94f7cc50bdc73d42a44b1fa94886921cb"],"state_sha256":"624c3b21011662f5f631750f497e67c2ea191626de2710463e42b2357f4db66d"}