{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GPCFRW5ZQXYWZOZMHFEJHMIJQV","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":"c4ffa184da4e83cc80d825c3d45744fd6480736b9b270034703b221301af217c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T14:24:11Z","title_canon_sha256":"442150e305d761bf966a7abaaf208294e5340311817fd5beb22ade0a76f3621f"},"schema_version":"1.0","source":{"id":"2605.21235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21235","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21235v1","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21235","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"GPCFRW5ZQXYW","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"GPCFRW5ZQXYWZOZM","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"GPCFRW5Z","created_at":"2026-05-21T01:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:d8bdda0ce9e532d5543bd3080ca24c8abb45e1070571ef227831ea26c53560af","target":"graph","created_at":"2026-05-21T01:05:45Z","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/2605.21235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bowen Deng, Jinghan Li, Liang Zhao, Xinyuan Chen, Yipeng Zhou, Zhe Yuan, Zhiqian Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T14:24:11Z","title":"LamPO: A Lambda Style Policy Optimization for Reasoning Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21235","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:c95f51c9568e8f6a06e54849edcfba530dd31053817f231b4f00f2df9db7ce04","target":"record","created_at":"2026-05-21T01:05:45Z","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":"c4ffa184da4e83cc80d825c3d45744fd6480736b9b270034703b221301af217c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T14:24:11Z","title_canon_sha256":"442150e305d761bf966a7abaaf208294e5340311817fd5beb22ade0a76f3621f"},"schema_version":"1.0","source":{"id":"2605.21235","kind":"arxiv","version":1}},"canonical_sha256":"33c458dbb985f16cbb2c394893b1098546476459af17c8ad69bc58bf8da2e970","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33c458dbb985f16cbb2c394893b1098546476459af17c8ad69bc58bf8da2e970","first_computed_at":"2026-05-21T01:05:45.025406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:45.025406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCwdk4s82wDy8EQd2b/JP5STkW6vtOFopXWj+nLZy1h08ic0Fun8Ft1HPFSYzqP9WokLfweH2MatX3qV1ElgAQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:45.026032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c95f51c9568e8f6a06e54849edcfba530dd31053817f231b4f00f2df9db7ce04","sha256:d8bdda0ce9e532d5543bd3080ca24c8abb45e1070571ef227831ea26c53560af"],"state_sha256":"1da7b84cb5e59306ed341f5c6b8d4141c8da6a5e7911b5e1d5a2d2e688bb2421"}