{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I5UVBOCKEPPAJBH4SWDPPURYSU","short_pith_number":"pith:I5UVBOCK","canonical_record":{"source":{"id":"2605.19416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:10:24Z","cross_cats_sorted":[],"title_canon_sha256":"09b36ebea38b8aa092162f469c106f3f18b1cc400c662e2ddf6f054f947f77c7","abstract_canon_sha256":"b7a82f0abdd2eb9403e3b2f5a9828f0d29451b65af54d20956feb0da44f78eea"},"schema_version":"1.0"},"canonical_sha256":"476950b84a23de0484fc9586f7d2389521efec0ef2d68c82066ed74991ccec6e","source":{"kind":"arxiv","id":"2605.19416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19416","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19416v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19416","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"I5UVBOCKEPPA","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"I5UVBOCKEPPAJBH4","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"I5UVBOCK","created_at":"2026-05-20T01:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I5UVBOCKEPPAJBH4SWDPPURYSU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:10:24Z","cross_cats_sorted":[],"title_canon_sha256":"09b36ebea38b8aa092162f469c106f3f18b1cc400c662e2ddf6f054f947f77c7","abstract_canon_sha256":"b7a82f0abdd2eb9403e3b2f5a9828f0d29451b65af54d20956feb0da44f78eea"},"schema_version":"1.0"},"canonical_sha256":"476950b84a23de0484fc9586f7d2389521efec0ef2d68c82066ed74991ccec6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:44.654396Z","signature_b64":"tb+Dfhmp4MleLxCjnFw1U2kch/ZuHdQ1AXdg/TPX6YdCn/pHpw04z+sL1QEA2mTKIt5AH8Ze3vc/dvDwahEADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"476950b84a23de0484fc9586f7d2389521efec0ef2d68c82066ed74991ccec6e","last_reissued_at":"2026-05-20T01:05:44.653161Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:44.653161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19416","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3hck9G19nUn1zrZahx5DIKsgvGcOR3kfTPnFGXmBWopv/ppHmDuKCHYyuhJwc3jYS4K9Db/9f68QOfXiCNwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:52:34.493029Z"},"content_sha256":"3b5de23d631c637e8a7bc981d1063adfdcd4919787caf31dfd34e0e7a0e32739","schema_version":"1.0","event_id":"sha256:3b5de23d631c637e8a7bc981d1063adfdcd4919787caf31dfd34e0e7a0e32739"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I5UVBOCKEPPAJBH4SWDPPURYSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LambdaPO: 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":"2026-05-19T06:10:24Z","abstract_excerpt":"Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory cohorts. However, the method's reliance on a monolithic statistical baseline, such as the group mean, collapses the relational topology of the trajectory space into a single scalar, thereby erasing the fine-grained preference information essential for navigating complex, rank-sensitive reward landscapes. To address this issue, we introduce a novel framework, Lambda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19416","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/2605.19416/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUMZZTfgNw6ok+CT2zhURhAY5ZwNEHQCQFBBocCI/5PllOmdosNCwCr2RfSZyupxuewuUwUF1xX7EKDyCO1eAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:52:34.493676Z"},"content_sha256":"425149130ca5cc25169c867f39e6ca9ff3e033309f9e9d3e86e1008f351a6d1e","schema_version":"1.0","event_id":"sha256:425149130ca5cc25169c867f39e6ca9ff3e033309f9e9d3e86e1008f351a6d1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/bundle.json","state_url":"https://pith.science/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T18:52:34Z","links":{"resolver":"https://pith.science/pith/I5UVBOCKEPPAJBH4SWDPPURYSU","bundle":"https://pith.science/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/bundle.json","state":"https://pith.science/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5UVBOCKEPPAJBH4SWDPPURYSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I5UVBOCKEPPAJBH4SWDPPURYSU","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":"b7a82f0abdd2eb9403e3b2f5a9828f0d29451b65af54d20956feb0da44f78eea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:10:24Z","title_canon_sha256":"09b36ebea38b8aa092162f469c106f3f18b1cc400c662e2ddf6f054f947f77c7"},"schema_version":"1.0","source":{"id":"2605.19416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19416","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19416v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19416","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"I5UVBOCKEPPA","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"I5UVBOCKEPPAJBH4","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"I5UVBOCK","created_at":"2026-05-20T01:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:425149130ca5cc25169c867f39e6ca9ff3e033309f9e9d3e86e1008f351a6d1e","target":"graph","created_at":"2026-05-20T01:05:44Z","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/2605.19416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory cohorts. However, the method's reliance on a monolithic statistical baseline, such as the group mean, collapses the relational topology of the trajectory space into a single scalar, thereby erasing the fine-grained preference information essential for navigating complex, rank-sensitive reward landscapes. To address this issue, we introduce a novel framework, Lambda","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":"2026-05-19T06:10:24Z","title":"LambdaPO: A Lambda Style Policy Optimization for Reasoning Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19416","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":"sha256:3b5de23d631c637e8a7bc981d1063adfdcd4919787caf31dfd34e0e7a0e32739","target":"record","created_at":"2026-05-20T01:05:44Z","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":"b7a82f0abdd2eb9403e3b2f5a9828f0d29451b65af54d20956feb0da44f78eea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:10:24Z","title_canon_sha256":"09b36ebea38b8aa092162f469c106f3f18b1cc400c662e2ddf6f054f947f77c7"},"schema_version":"1.0","source":{"id":"2605.19416","kind":"arxiv","version":1}},"canonical_sha256":"476950b84a23de0484fc9586f7d2389521efec0ef2d68c82066ed74991ccec6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"476950b84a23de0484fc9586f7d2389521efec0ef2d68c82066ed74991ccec6e","first_computed_at":"2026-05-20T01:05:44.653161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:44.653161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tb+Dfhmp4MleLxCjnFw1U2kch/ZuHdQ1AXdg/TPX6YdCn/pHpw04z+sL1QEA2mTKIt5AH8Ze3vc/dvDwahEADw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:44.654396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b5de23d631c637e8a7bc981d1063adfdcd4919787caf31dfd34e0e7a0e32739","sha256:425149130ca5cc25169c867f39e6ca9ff3e033309f9e9d3e86e1008f351a6d1e"],"state_sha256":"7cb9f48ba385b24f19f057992688fc081381a128c0fa77094c820664bc480a1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2BaEDbN2tJxXrSTxZZ53MhEBGZep9nDsDDz6FN+CdFmDOfFsta6LTls9uJ+9Dppht0XN5wVTmcBcuTXsI8qBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:52:34.496841Z","bundle_sha256":"6213d8957e8b9fff2fca3e69f95493e38e3b20947028860274e89f86881b27b7"}}