{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DUE2XCBYQXFXERPS4L7OH2YFHS","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a229448a39aa2a87e5886160715e3d966e78eb6b979da399f551732ce35604a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-28T07:28:38Z","title_canon_sha256":"e7f745affe74d18293b97531e7a3f7c75ad1fbd6ac9ed6f8b8be2adea67cd50d"},"schema_version":"1.0","source":{"id":"2607.26102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26102","created_at":"2026-07-30T00:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26102v1","created_at":"2026-07-30T00:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26102","created_at":"2026-07-30T00:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"DUE2XCBYQXFX","created_at":"2026-07-30T00:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"DUE2XCBYQXFXERPS","created_at":"2026-07-30T00:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"DUE2XCBY","created_at":"2026-07-30T00:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:7162f2bf9e811f0905effc6cf200ad19420230b11b4aba5cf9e0dbf4eb66323d","target":"graph","created_at":"2026-07-30T00:08:21Z","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/2607.26102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference. This conflates producing a correct conclusion with producing a valid derivation an invalid chain can accidentally reach the right answer, while a valid calculation can be followed by a transcription error. We call this mismatch the reasoning answer consistency gap. This framework paper introduces the Reasoning Answer Faithfulness Score (RAFS), a reference free, instance level diagnostic of whether an emitted mathematical trace is locally credible, supports its answer, and is stab","authors_text":"Atul, Divya Mishra, Mehul Kumar Das, Varun Shukla, Vivek Shukla","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-28T07:28:38Z","title":"A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26102","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":"sha256:0d14ed308675cefe31cd8d25ebe5a6e5d5c9e15b318c9902a2bc3040f9e97f3d","target":"record","created_at":"2026-07-30T00:08:21Z","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":"2a229448a39aa2a87e5886160715e3d966e78eb6b979da399f551732ce35604a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-28T07:28:38Z","title_canon_sha256":"e7f745affe74d18293b97531e7a3f7c75ad1fbd6ac9ed6f8b8be2adea67cd50d"},"schema_version":"1.0","source":{"id":"2607.26102","kind":"arxiv","version":1}},"canonical_sha256":"1d09ab883885cb7245f2e2fee3eb053c84f8eb9e1b3eae27404e0614a5647648","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d09ab883885cb7245f2e2fee3eb053c84f8eb9e1b3eae27404e0614a5647648","first_computed_at":"2026-07-30T00:08:21.313378Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T00:08:21.313378Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d14ed308675cefe31cd8d25ebe5a6e5d5c9e15b318c9902a2bc3040f9e97f3d","sha256:7162f2bf9e811f0905effc6cf200ad19420230b11b4aba5cf9e0dbf4eb66323d","sha256:55e9901e9c0e495c7fdeccf89487fb82b32ae19c0a2b1a8bbbbc8e2e1fc5e3a2"],"state_sha256":"49b334e4433031c584a5660a62f06be19d6484c47765641a39120fe0111d3335"}