{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GPCFRW5ZQXYWZOZMHFEJHMIJQV","short_pith_number":"pith:GPCFRW5Z","schema_version":"1.0","canonical_sha256":"33c458dbb985f16cbb2c394893b1098546476459af17c8ad69bc58bf8da2e970","source":{"kind":"arxiv","id":"2605.21235","version":1},"attestation_state":"computed","paper":{"title":"LamPO: A Lambda Style Policy Optimization for Reasoning Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Deng, Jinghan Li, Liang Zhao, Xinyuan Chen, Yipeng Zhou, Zhe Yuan, Zhiqian Chen","submitted_at":"2026-05-20T14:24:11Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative objectives, such as GRPO, summarize each sampled group with scalar statistics and therefore discard fine-grained relational information among candidate responses. This weakens credit assignment under sparse outcome rewards, especially when multiple generated solutions differ only subtly in reasoning quality. We propose \\textbf{LamPO}, a \\textbf{Lambda-Style Poli"},"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":"2605.21235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T14:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"442150e305d761bf966a7abaaf208294e5340311817fd5beb22ade0a76f3621f","abstract_canon_sha256":"c4ffa184da4e83cc80d825c3d45744fd6480736b9b270034703b221301af217c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:45.026032Z","signature_b64":"BCwdk4s82wDy8EQd2b/JP5STkW6vtOFopXWj+nLZy1h08ic0Fun8Ft1HPFSYzqP9WokLfweH2MatX3qV1ElgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c458dbb985f16cbb2c394893b1098546476459af17c8ad69bc58bf8da2e970","last_reissued_at":"2026-05-21T01:05:45.025406Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:45.025406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LamPO: A Lambda Style Policy Optimization for Reasoning Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Deng, Jinghan Li, Liang Zhao, Xinyuan Chen, Yipeng Zhou, Zhe Yuan, Zhiqian Chen","submitted_at":"2026-05-20T14:24:11Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative objectives, such as GRPO, summarize each sampled group with scalar statistics and therefore discard fine-grained relational information among candidate responses. This weakens credit assignment under sparse outcome rewards, especially when multiple generated solutions differ only subtly in reasoning quality. We propose \\textbf{LamPO}, a \\textbf{Lambda-Style Poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21235","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.21235/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2605.21235","created_at":"2026-05-21T01:05:45.025517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21235v1","created_at":"2026-05-21T01:05:45.025517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21235","created_at":"2026-05-21T01:05:45.025517+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPCFRW5ZQXYW","created_at":"2026-05-21T01:05:45.025517+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPCFRW5ZQXYWZOZM","created_at":"2026-05-21T01:05:45.025517+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPCFRW5Z","created_at":"2026-05-21T01:05:45.025517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV","json":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV.json","graph_json":"https://pith.science/api/pith-number/GPCFRW5ZQXYWZOZMHFEJHMIJQV/graph.json","events_json":"https://pith.science/api/pith-number/GPCFRW5ZQXYWZOZMHFEJHMIJQV/events.json","paper":"https://pith.science/paper/GPCFRW5Z"},"agent_actions":{"view_html":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV","download_json":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV.json","view_paper":"https://pith.science/paper/GPCFRW5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21235&json=true","fetch_graph":"https://pith.science/api/pith-number/GPCFRW5ZQXYWZOZMHFEJHMIJQV/graph.json","fetch_events":"https://pith.science/api/pith-number/GPCFRW5ZQXYWZOZMHFEJHMIJQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV/action/storage_attestation","attest_author":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV/action/author_attestation","sign_citation":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV/action/citation_signature","submit_replication":"https://pith.science/pith/GPCFRW5ZQXYWZOZMHFEJHMIJQV/action/replication_record"}},"created_at":"2026-05-21T01:05:45.025517+00:00","updated_at":"2026-05-21T01:05:45.025517+00:00"}