{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:737LKEDPBXREIF3LTEMJ57EIL3","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":"82082ee2070f3522b2773346f824273a99fe47cb9e39c72d1452aed96a563a37","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T15:27:34Z","title_canon_sha256":"1b358b977e70752e98dbcbabe5cb9351cccf7c8075f16468e345993f61002a30"},"schema_version":"1.0","source":{"id":"2604.28005","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.28005","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2604.28005v2","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.28005","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"737LKEDPBXRE","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"737LKEDPBXREIF3L","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"737LKEDP","created_at":"2026-05-20T00:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:51df32c4f12c4189c2f36680cc53fff1f25ab50fa9e78ce826292466456e3a42","target":"graph","created_at":"2026-05-20T00:02:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Kernel smoothing applied to a small number of reasoning traces per prompt can produce sufficiently unbiased and low-variance estimates of the true value function in the high-dimensional, discrete space of LLM outputs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Kernel smoothing yields accurate value and gradient estimates for low-variance policy learning in LLM reasoning under tight per-prompt sampling budgets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning."}],"snapshot_sha256":"4e51d9dc8e7157fb6d02d3fd657553107212253a70ec9ad1e66d75340fe6546f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:41:39.195940Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.28005/integrity.json","findings":[],"snapshot_sha256":"502ab46ad05790b13427aaf41050b2578545341505d347dddf670c30aa51c5cb","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network to estimate the value function of the learning policy in order to reduce the variance of the policy gradient. However, estimating and maintaining such a value network incurs substantial computational and memory overhead. The second avoids training a value network by approximating the value function using sample averages. However, it samples a large number of ","authors_text":"Chengchun Shi, Hongyi Zhou, Jin Zhu, Kai Ye, Shijin Gong, Xinyu Zhang","cross_cats":["stat.ML"],"headline":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T15:27:34Z","title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.28005","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T06:54:54.394441Z","id":"7ea2283d-b225-4cef-aacf-67b8e11dc751","model_set":{"reader":"grok-4.3"},"one_line_summary":"Kernel smoothing yields accurate value and gradient estimates for low-variance policy learning in LLM reasoning under tight per-prompt sampling budgets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.","strongest_claim":"Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.","weakest_assumption":"Kernel smoothing applied to a small number of reasoning traces per prompt can produce sufficiently unbiased and low-variance estimates of the true value function in the high-dimensional, discrete space of LLM outputs."}},"verdict_id":"7ea2283d-b225-4cef-aacf-67b8e11dc751"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6dc65c8ed540affde2d79dc5a1048afc49b8cb60255b979e683b9264eba34c93","target":"record","created_at":"2026-05-20T00:02:11Z","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":"82082ee2070f3522b2773346f824273a99fe47cb9e39c72d1452aed96a563a37","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T15:27:34Z","title_canon_sha256":"1b358b977e70752e98dbcbabe5cb9351cccf7c8075f16468e345993f61002a30"},"schema_version":"1.0","source":{"id":"2604.28005","kind":"arxiv","version":2}},"canonical_sha256":"fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210","first_computed_at":"2026-05-20T00:02:11.931112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:11.931112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NjcBmI130HhzzKu9JihMTST2PFWeTAdW3Cq3T2TiQ/dS7roweeAamaT8xBhJ1VhONFDnMOK30LC4SJ+orIglAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:11.931886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.28005","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dc65c8ed540affde2d79dc5a1048afc49b8cb60255b979e683b9264eba34c93","sha256:51df32c4f12c4189c2f36680cc53fff1f25ab50fa9e78ce826292466456e3a42"],"state_sha256":"4d407cd8e1ab3e920d11706c32f71f07bbb38d2a484e6f809c5b6b06612b48c4"}