{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BCAIFHOP6NLL7UEUZTO5NQ5J2X","short_pith_number":"pith:BCAIFHOP","schema_version":"1.0","canonical_sha256":"0880829dcff356bfd094ccddd6c3a9d5e6d42ed0aff31d36e228015d8e78af88","source":{"kind":"arxiv","id":"2605.06139","version":2},"attestation_state":"computed","paper":{"title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Group-based RL for LLMs implicitly projects policies toward targets on the response simplex; LPO makes the projection explicit and exact.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clive Bai, Heming Zou, Kai Yang, Lizhou Cai, Qi Wang, Saiyong Yang, Weijie Liu, Wutong Xu, Xiangyang Ji, Yangkun Chen, Yingyue Li, Yixiu Mao, Yuhang Jiang, Yun Qu","submitted_at":"2026-05-07T12:38:17Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient is prevalent, which samples a group of responses per prompt and updates the policy via group-relative advantage signals. This work reveals that these optimization strategies share a common geometric structure: each implicitly defines a target distribution on the response simplex and projects toward it via first-order approximation. Building on this insight, we propose Listwise P"},"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":"2605.06139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T12:38:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a779b4493234406e077ac567af69c5e1cdcfa6ec05c6092ab9b0e7fd7c50c8f","abstract_canon_sha256":"3cd68bc954a2a0014707915b20910a779644b64c252b024558bfbda80aa3dd1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:20.390715Z","signature_b64":"x+sbUNzZHcINjHYoIH3PZPGboKhMqKgC0MLSwboqfhK4RW7fciZQIl1EFC+WdyYA0C8M+QT+dvoqgZ3JMLfxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0880829dcff356bfd094ccddd6c3a9d5e6d42ed0aff31d36e228015d8e78af88","last_reissued_at":"2026-05-21T01:05:20.390028Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:20.390028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Group-based RL for LLMs implicitly projects policies toward targets on the response simplex; LPO makes the projection explicit and exact.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clive Bai, Heming Zou, Kai Yang, Lizhou Cai, Qi Wang, Saiyong Yang, Weijie Liu, Wutong Xu, Xiangyang Ji, Yangkun Chen, Yingyue Li, Yixiu Mao, Yuhang Jiang, Yun Qu","submitted_at":"2026-05-07T12:38:17Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient is prevalent, which samples a group of responses per prompt and updates the policy via group-relative advantage signals. This work reveals that these optimization strategies share a common geometric structure: each implicitly defines a target distribution on the response simplex and projects toward it via first-order approximation. Building on this insight, we propose Listwise P"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LPO provides (i) monotonic improvement on the listwise objective with bounded, zero-sum, and self-correcting projection gradients, and (ii) flexibility in divergence selection with distinct structural properties through the decoupled projection step.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the implicit targets defined by existing group-based methods can be exactly recovered or improved upon by restricting the proximal RL objective to the response simplex and performing exact divergence minimization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LPO reframes group-based RLVR as explicit target-projection on the LLM response simplex and performs exact divergence minimization to achieve monotonic listwise improvement with bounded gradients.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Group-based RL for LLMs implicitly projects policies toward targets on the response simplex; LPO makes the projection explicit and exact.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2a3211ca39bba360b8e843db855779fe770eacd7c73506edb778bd9392ae86b5"},"source":{"id":"2605.06139","kind":"arxiv","version":2},"verdict":{"id":"6cc46c2c-bc25-4323-9757-eb4547d0eca6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T13:51:51.705037Z","strongest_claim":"LPO provides (i) monotonic improvement on the listwise objective with bounded, zero-sum, and self-correcting projection gradients, and (ii) flexibility in divergence selection with distinct structural properties through the decoupled projection step.","one_line_summary":"LPO reframes group-based RLVR as explicit target-projection on the LLM response simplex and performs exact divergence minimization to achieve monotonic listwise improvement with bounded gradients.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the implicit targets defined by existing group-based methods can be exactly recovered or improved upon by restricting the proximal RL objective to the response simplex and performing exact divergence minimization.","pith_extraction_headline":"Group-based RL for LLMs implicitly projects policies toward targets on the response simplex; LPO makes the projection explicit and exact."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06139/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T13:02:04.296347Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T08:36:39.607964Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.376208Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:55:45.727798Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"aa11b66d4e677d0cc7dcc831cb371755b7e60c53f031d482c4143a2cf307e86c"},"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":"2605.06139","created_at":"2026-05-21T01:05:20.390120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06139v2","created_at":"2026-05-21T01:05:20.390120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06139","created_at":"2026-05-21T01:05:20.390120+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCAIFHOP6NLL","created_at":"2026-05-21T01:05:20.390120+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCAIFHOP6NLL7UEU","created_at":"2026-05-21T01:05:20.390120+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCAIFHOP","created_at":"2026-05-21T01:05:20.390120+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/BCAIFHOP6NLL7UEUZTO5NQ5J2X","json":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X.json","graph_json":"https://pith.science/api/pith-number/BCAIFHOP6NLL7UEUZTO5NQ5J2X/graph.json","events_json":"https://pith.science/api/pith-number/BCAIFHOP6NLL7UEUZTO5NQ5J2X/events.json","paper":"https://pith.science/paper/BCAIFHOP"},"agent_actions":{"view_html":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X","download_json":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X.json","view_paper":"https://pith.science/paper/BCAIFHOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06139&json=true","fetch_graph":"https://pith.science/api/pith-number/BCAIFHOP6NLL7UEUZTO5NQ5J2X/graph.json","fetch_events":"https://pith.science/api/pith-number/BCAIFHOP6NLL7UEUZTO5NQ5J2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X/action/storage_attestation","attest_author":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X/action/author_attestation","sign_citation":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X/action/citation_signature","submit_replication":"https://pith.science/pith/BCAIFHOP6NLL7UEUZTO5NQ5J2X/action/replication_record"}},"created_at":"2026-05-21T01:05:20.390120+00:00","updated_at":"2026-05-21T01:05:20.390120+00:00"}