{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OFRQ6TRF3BZXYCAY7DWEPVWOWL","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":"861db83cbff771e04b10ad96c1d2e9a50229e460a4af80edb06031849e7953b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T00:55:13Z","title_canon_sha256":"4ddf9c1dc1cdb3fdd4098a2c2958d1e590cf6940988f074d0aeed0143324742d"},"schema_version":"1.0","source":{"id":"2605.21851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21851","created_at":"2026-05-22T01:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21851v1","created_at":"2026-05-22T01:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21851","created_at":"2026-05-22T01:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"OFRQ6TRF3BZX","created_at":"2026-05-22T01:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"OFRQ6TRF3BZXYCAY","created_at":"2026-05-22T01:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"OFRQ6TRF","created_at":"2026-05-22T01:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:e4d1973606f090cdb67df16ea73d32cd905eda612f5a83373321b994b1cb1950","target":"graph","created_at":"2026-05-22T01:04:11Z","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/2605.21851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advantage to every token, diluting the signal at pivotal reasoning steps and injecting noise at uninformative ones. Critic-free alternatives derived from on-policy distillation supply per-token signals through oracle-conditioned likelihood ratios, yet apply each signal in isolation from the trajectory-level evidence accumulated up to that position. We propose Oracle-Prompted Policy Optimization (OPPO), which rests on a sing","authors_text":"Rui Miao, Tian Lan, Yu Li, Zhengling Qi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T00:55:13Z","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21851","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":"sha256:7d3d7e33ed4c484b9476dc85bfc7b25ec6f5427801fbd6bc3a625963893241ae","target":"record","created_at":"2026-05-22T01:04:11Z","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":"861db83cbff771e04b10ad96c1d2e9a50229e460a4af80edb06031849e7953b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T00:55:13Z","title_canon_sha256":"4ddf9c1dc1cdb3fdd4098a2c2958d1e590cf6940988f074d0aeed0143324742d"},"schema_version":"1.0","source":{"id":"2605.21851","kind":"arxiv","version":1}},"canonical_sha256":"71630f4e25d8737c0818f8ec47d6ceb2f430eb1c81fea15777af6c4de11300ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71630f4e25d8737c0818f8ec47d6ceb2f430eb1c81fea15777af6c4de11300ca","first_computed_at":"2026-05-22T01:04:11.173634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:11.173634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d/h2m5gFZYaxFsrNgpr8CcvnAbwvk1pNjeB6mkaBW/QrFqrp4L3RbUjUQgahu9k3MGtJLIjDDf6V2/qTFyZfBg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:11.174382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d3d7e33ed4c484b9476dc85bfc7b25ec6f5427801fbd6bc3a625963893241ae","sha256:e4d1973606f090cdb67df16ea73d32cd905eda612f5a83373321b994b1cb1950"],"state_sha256":"08fec1f63d67fc81bf1f2efdc0edcebf1b2a87ba0e9559c705d964dc31cb8d0f"}