{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MHD3T642PP6QJNUQG5ZDV4VJI3","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":"29119602cfcf05b64166e977ab0fe6d49fa30d69360cf1c0669e9324ff2cba9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T21:37:20Z","title_canon_sha256":"c41cdddb2e08075681dd000682259feb3a4ca0ae391a997cf86e53066010cfbb"},"schema_version":"1.0","source":{"id":"2605.27712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27712","created_at":"2026-05-28T01:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27712v1","created_at":"2026-05-28T01:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27712","created_at":"2026-05-28T01:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"MHD3T642PP6Q","created_at":"2026-05-28T01:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"MHD3T642PP6QJNUQ","created_at":"2026-05-28T01:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"MHD3T642","created_at":"2026-05-28T01:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:136ba14e4ae0a7b8cdc006a2e39630496326ce0e7ccf9481b28d853f85406cbd","target":"graph","created_at":"2026-05-28T01:04:46Z","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/2605.27712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, $P(y=1 \\mid o_{1:t})$, using prefix-safe observations. Sequential Bayesian Belief Tracking (SBBT) calibrates observation likelihoods and recursively updates a two-state belief, providing a common tracker for scalar scores, text and self-verification markers, hidden clusters, token-pooling probes, and latent-trajectory features. Across generated open-weight traces on MATH-500, GSM8K, AIME 2025, and RIMO-N, probability quality and ranking separate: score-only ","authors_text":"Yulong Liu, Yunyi Li, Zhenghan Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T21:37:20Z","title":"Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27712","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":"sha256:37977d67340ca37f7da65c42c5d4792c12213ad049df8935ec3bad4764585f61","target":"record","created_at":"2026-05-28T01:04:46Z","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":"29119602cfcf05b64166e977ab0fe6d49fa30d69360cf1c0669e9324ff2cba9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T21:37:20Z","title_canon_sha256":"c41cdddb2e08075681dd000682259feb3a4ca0ae391a997cf86e53066010cfbb"},"schema_version":"1.0","source":{"id":"2605.27712","kind":"arxiv","version":1}},"canonical_sha256":"61c7b9fb9a7bfd04b69037723af2a946c18afe217294fb7fa5c679fd33f96ba0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61c7b9fb9a7bfd04b69037723af2a946c18afe217294fb7fa5c679fd33f96ba0","first_computed_at":"2026-05-28T01:04:46.931749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:46.931749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vM1Zv5kRHQvRBof0jWmmczVctxAraDMvxHI+ByZ2sNuah1bb+N91mJZwtgVlurm0OrwDbyvBrPPHjlXt4xVRCg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:46.932082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37977d67340ca37f7da65c42c5d4792c12213ad049df8935ec3bad4764585f61","sha256:136ba14e4ae0a7b8cdc006a2e39630496326ce0e7ccf9481b28d853f85406cbd"],"state_sha256":"0ace083ada904feb6d8b44822cc8acc1aa6adf9c44cc0740809cc26f7502d882"}