{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:737LKEDPBXREIF3LTEMJ57EIL3","short_pith_number":"pith:737LKEDP","schema_version":"1.0","canonical_sha256":"fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210","source":{"kind":"arxiv","id":"2604.28005","version":2},"attestation_state":"computed","paper":{"title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengchun Shi, Hongyi Zhou, Jin Zhu, Kai Ye, Shijin Gong, Xinyu Zhang","submitted_at":"2026-04-30T15:27:34Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.28005","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T15:27:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1b358b977e70752e98dbcbabe5cb9351cccf7c8075f16468e345993f61002a30","abstract_canon_sha256":"82082ee2070f3522b2773346f824273a99fe47cb9e39c72d1452aed96a563a37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:11.931886Z","signature_b64":"NjcBmI130HhzzKu9JihMTST2PFWeTAdW3Cq3T2TiQ/dS7roweeAamaT8xBhJ1VhONFDnMOK30LC4SJ+orIglAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210","last_reissued_at":"2026-05-20T00:02:11.931112Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:11.931112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengchun Shi, Hongyi Zhou, Jin Zhu, Kai Ye, Shijin Gong, Xinyu Zhang","submitted_at":"2026-04-30T15:27:34Z","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 "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Kernel smoothing yields accurate value and gradient estimates for low-variance policy learning in LLM reasoning under tight per-prompt sampling budgets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4e51d9dc8e7157fb6d02d3fd657553107212253a70ec9ad1e66d75340fe6546f"},"source":{"id":"2604.28005","kind":"arxiv","version":2},"verdict":{"id":"7ea2283d-b225-4cef-aacf-67b8e11dc751","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T06:54:54.394441Z","strongest_claim":"Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.","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","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.","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."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.28005/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T18:41:39.195940Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"502ab46ad05790b13427aaf41050b2578545341505d347dddf670c30aa51c5cb"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.28005","created_at":"2026-05-20T00:02:11.931237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.28005v2","created_at":"2026-05-20T00:02:11.931237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.28005","created_at":"2026-05-20T00:02:11.931237+00:00"},{"alias_kind":"pith_short_12","alias_value":"737LKEDPBXRE","created_at":"2026-05-20T00:02:11.931237+00:00"},{"alias_kind":"pith_short_16","alias_value":"737LKEDPBXREIF3L","created_at":"2026-05-20T00:02:11.931237+00:00"},{"alias_kind":"pith_short_8","alias_value":"737LKEDP","created_at":"2026-05-20T00:02:11.931237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.13284","citing_title":"Learning Perturbations to Extrapolate Your LLM","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04344","citing_title":"Perturbation is All You Need for Extrapolating Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3","json":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3.json","graph_json":"https://pith.science/api/pith-number/737LKEDPBXREIF3LTEMJ57EIL3/graph.json","events_json":"https://pith.science/api/pith-number/737LKEDPBXREIF3LTEMJ57EIL3/events.json","paper":"https://pith.science/paper/737LKEDP"},"agent_actions":{"view_html":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3","download_json":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3.json","view_paper":"https://pith.science/paper/737LKEDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.28005&json=true","fetch_graph":"https://pith.science/api/pith-number/737LKEDPBXREIF3LTEMJ57EIL3/graph.json","fetch_events":"https://pith.science/api/pith-number/737LKEDPBXREIF3LTEMJ57EIL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3/action/storage_attestation","attest_author":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3/action/author_attestation","sign_citation":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3/action/citation_signature","submit_replication":"https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3/action/replication_record"}},"created_at":"2026-05-20T00:02:11.931237+00:00","updated_at":"2026-05-20T00:02:11.931237+00:00"}