{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JSGQNCS373K3IA2JVXJNDZTAHC","short_pith_number":"pith:JSGQNCS3","canonical_record":{"source":{"id":"2608.02149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T12:34:04Z","cross_cats_sorted":[],"title_canon_sha256":"ce50c9438758c2421233e6b5665b28a1a4cc02fbbae73ce1eadfc4157a7322e0","abstract_canon_sha256":"408818e9b99934ebf49c99e7f856dbe2972145fd892ebfb6e175e6cc9b35cdef"},"schema_version":"1.0"},"canonical_sha256":"4c8d068a5bfed5b40349add2d1e66038acec8c2f36076f1ce2af35dc3673dd9a","source":{"kind":"arxiv","id":"2608.02149","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JSGQNCS373K3IA2JVXJNDZTAHC","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T12:34:04Z","cross_cats_sorted":[],"title_canon_sha256":"ce50c9438758c2421233e6b5665b28a1a4cc02fbbae73ce1eadfc4157a7322e0","abstract_canon_sha256":"408818e9b99934ebf49c99e7f856dbe2972145fd892ebfb6e175e6cc9b35cdef"},"schema_version":"1.0"},"canonical_sha256":"4c8d068a5bfed5b40349add2d1e66038acec8c2f36076f1ce2af35dc3673dd9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:06.877112Z","signature_b64":"/VTMIQ4NedIRTCjB0Xjm2Rtp04fIbH92N+d7LoI34yBZI1M3G1BoDhu76YiqZRhckCGvIxo857SEV1GKwZ+7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8d068a5bfed5b40349add2d1e66038acec8c2f36076f1ce2af35dc3673dd9a","last_reissued_at":"2026-08-04T02:11:06.875511Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:06.875511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02149","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":"2026-08-04T02:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWtuePaLzc+qlxvNrXhjejFOqJ8WhmAp39xBIe/w9iYPwsv44FZDUUZwRmMDZzP+93T5+E/E79c10vkj1yEsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:16.564672Z"},"content_sha256":"73d46fd4bef1de8bafa8b1f934390daabf5f850bacd858098213f901c172fe83","schema_version":"1.0","event_id":"sha256:73d46fd4bef1de8bafa8b1f934390daabf5f850bacd858098213f901c172fe83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JSGQNCS373K3IA2JVXJNDZTAHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fan Xu, Haoxiang Zhang, Jiaxin Ding, Luoyi Fu, Xin Ding, Yijun Zhang, Yule Xie","submitted_at":"2026-08-03T12:34:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02149","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/2608.02149/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":"2026-08-04T02:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/ATzljuIXvQ6GaidYWtLHHw+d1r/p8+DyNkWlhMXrnI+dhaXXVI9e5t8RsUNk26T4I3k+wsLElXOSpWSMkGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:16.565315Z"},"content_sha256":"044027ed67cf3bc9893e4ffcaa7f4fbcb0df3cfa8d626a3eaa2694915c33c870","schema_version":"1.0","event_id":"sha256:044027ed67cf3bc9893e4ffcaa7f4fbcb0df3cfa8d626a3eaa2694915c33c870"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSGQNCS373K3IA2JVXJNDZTAHC/bundle.json","state_url":"https://pith.science/pith/JSGQNCS373K3IA2JVXJNDZTAHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSGQNCS373K3IA2JVXJNDZTAHC/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":"2026-08-05T19:48:16Z","links":{"resolver":"https://pith.science/pith/JSGQNCS373K3IA2JVXJNDZTAHC","bundle":"https://pith.science/pith/JSGQNCS373K3IA2JVXJNDZTAHC/bundle.json","state":"https://pith.science/pith/JSGQNCS373K3IA2JVXJNDZTAHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSGQNCS373K3IA2JVXJNDZTAHC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2IaJGWulScET9h5dmQbMByfBQPgu5iOX4l/I3o7gb7rM1OOB1H2ZbMeghSu6p5gLSxJPGkeQzcn1IVPAyPRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:48:16.571779Z","bundle_sha256":"fc71b8b91653422b5593a2670dee922a8e5d12594141f7bfb5043d3f29e028a1"}}