{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HS5J7IJ7DHPZA5INVNU7MESLOG","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":"cfa64176186bddd4008a6714986d19f4842d612bfeee57626e7d613d45243cfa","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-19T18:20:38Z","title_canon_sha256":"8ea77c80f42142f534b37783da74b172cf56e8e5d4cb37f3f9d13bd04b056d24"},"schema_version":"1.0","source":{"id":"2508.15842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15842","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15842v1","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15842","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"HS5J7IJ7DHPZ","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"HS5J7IJ7DHPZA5IN","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"HS5J7IJ7","created_at":"2026-07-05T11:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:4f44002c3459bd559fa83e04c228f2e291b818d10c784c960e005e8fcfaee651","target":"graph","created_at":"2026-07-05T11:57:21Z","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/2508.15842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning Large Language Models (LLMs) with reinforcement learning to produce an explicit Chain-of-Thought (CoT) before answering produces models that consistently raise overall performance on code, math, and general-knowledge benchmarks. However, on benchmarks where LLMs currently achieve low accuracy, such as Humanity's Last Exam (HLE), they often report high self-confidence, reflecting poor calibration. Here, we test whether measurable properties of the CoT provide reliable signals of an LLM's internal confidence in its answers. We analyze three feature classes: (i) CoT length, (ii) intra","authors_text":"Andres Algaba, Arne Vanhoyweghen, Brecht Verbeken, Vincent Ginis","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-19T18:20:38Z","title":"Lexical Hints of Accuracy in LLM Reasoning Chains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15842","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":"sha256:142f8eba3fa6246d1f221e5063fecf49d680e51736c3e81b440fc25e72581af3","target":"record","created_at":"2026-07-05T11:57:21Z","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":"cfa64176186bddd4008a6714986d19f4842d612bfeee57626e7d613d45243cfa","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-19T18:20:38Z","title_canon_sha256":"8ea77c80f42142f534b37783da74b172cf56e8e5d4cb37f3f9d13bd04b056d24"},"schema_version":"1.0","source":{"id":"2508.15842","kind":"arxiv","version":1}},"canonical_sha256":"3cba9fa13f19df90750dab69f6124b7197b89173425da5258bcebc9e3cc77e5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cba9fa13f19df90750dab69f6124b7197b89173425da5258bcebc9e3cc77e5b","first_computed_at":"2026-07-05T11:57:21.851051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:21.851051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y/9ZwWT5B8h124GLh8NZE+YF7fjdUOMwaj6ACqVTaMUQtZkZCfu64SZhY10kmQT3zt4yoHF/3MvcOq+0Wt1tDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:21.851470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:142f8eba3fa6246d1f221e5063fecf49d680e51736c3e81b440fc25e72581af3","sha256:4f44002c3459bd559fa83e04c228f2e291b818d10c784c960e005e8fcfaee651"],"state_sha256":"08478ed6a024380ae1e11b8e517100f87e7cafa10a2cc18bdfead6eaf37a53cd"}