{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JSGQNCS373K3IA2JVXJNDZTAHC","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":"408818e9b99934ebf49c99e7f856dbe2972145fd892ebfb6e175e6cc9b35cdef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T12:34:04Z","title_canon_sha256":"ce50c9438758c2421233e6b5665b28a1a4cc02fbbae73ce1eadfc4157a7322e0"},"schema_version":"1.0","source":{"id":"2608.02149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02149","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02149v1","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02149","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"JSGQNCS373K3","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"JSGQNCS373K3IA2J","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"JSGQNCS3","created_at":"2026-08-04T02:11:06Z"}],"graph_snapshots":[{"event_id":"sha256:044027ed67cf3bc9893e4ffcaa7f4fbcb0df3cfa8d626a3eaa2694915c33c870","target":"graph","created_at":"2026-08-04T02:11:06Z","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/2608.02149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has become a central paradigm for improving the reasoning capabilities of large language models. Existing methods generally aim to reduce the failure probabilities induced across problems. In this paper, we introduce a moment-based perspective on policy optimization for LLM reasoning by treating the failure probability of a randomly sampled problem as a random variable and characterizing optimization objectives through its moments. Under this perspective, many existing methods optimize only a single moment of the failure-probability distribution, leaving its broader dist","authors_text":"Fan Xu, Haoxiang Zhang, Jiaxin Ding, Luoyi Fu, Xin Ding, Yijun Zhang, Yule Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T12:34:04Z","title":"Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02149","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":"sha256:73d46fd4bef1de8bafa8b1f934390daabf5f850bacd858098213f901c172fe83","target":"record","created_at":"2026-08-04T02:11:06Z","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":"408818e9b99934ebf49c99e7f856dbe2972145fd892ebfb6e175e6cc9b35cdef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T12:34:04Z","title_canon_sha256":"ce50c9438758c2421233e6b5665b28a1a4cc02fbbae73ce1eadfc4157a7322e0"},"schema_version":"1.0","source":{"id":"2608.02149","kind":"arxiv","version":1}},"canonical_sha256":"4c8d068a5bfed5b40349add2d1e66038acec8c2f36076f1ce2af35dc3673dd9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c8d068a5bfed5b40349add2d1e66038acec8c2f36076f1ce2af35dc3673dd9a","first_computed_at":"2026-08-04T02:11:06.875511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:06.875511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/VTMIQ4NedIRTCjB0Xjm2Rtp04fIbH92N+d7LoI34yBZI1M3G1BoDhu76YiqZRhckCGvIxo857SEV1GKwZ+7BQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:06.877112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d46fd4bef1de8bafa8b1f934390daabf5f850bacd858098213f901c172fe83","sha256:044027ed67cf3bc9893e4ffcaa7f4fbcb0df3cfa8d626a3eaa2694915c33c870"],"state_sha256":"63f3b416cfa14eee3d6e2159ff3a7a9f2ff638db14263eb9f29df0e6b39fd151"}