{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P35KLMVJQGT4BBRORPTXFZS7KA","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":"f8d15fab0c1a39eedd0236be320395a3ae48394f5b5a76719ffeef1ebe6bd04b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:56:24Z","title_canon_sha256":"b1cbb16f2f1a29e7cc9a75a13b405deced3993ac052c812fbc2508da4964981c"},"schema_version":"1.0","source":{"id":"2506.03723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03723","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03723v1","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03723","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_12","alias_value":"P35KLMVJQGT4","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_16","alias_value":"P35KLMVJQGT4BBRO","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_8","alias_value":"P35KLMVJ","created_at":"2026-07-05T11:15:50Z"}],"graph_snapshots":[{"event_id":"sha256:7e9d241c17c2343d49caba7f7f903c1f2bd3189273729fc48878f63f71822fc6","target":"graph","created_at":"2026-07-05T11:15:50Z","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/2506.03723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence calibration for chain-of-thought (CoT) reasoning remains largely unexplored. Surprisingly, we find that supervised fine-tuning with scalar confidence labels alone suffices to elicit self-verification behavior of language models, without any explicit reasoning supervision or reinforcement learning-based rewards. Despite being trained only to produce a verbali","authors_text":"Chaeyun Jang, Hyungi Lee, Juho Lee, Moonseok Choi, Yegon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:56:24Z","title":"Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03723","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:ca89c6bbb1b2eaf741ccaea27aa3266c6fd3a248a7e0cd0673ccca3a15ab9e7a","target":"record","created_at":"2026-07-05T11:15:50Z","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":"f8d15fab0c1a39eedd0236be320395a3ae48394f5b5a76719ffeef1ebe6bd04b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:56:24Z","title_canon_sha256":"b1cbb16f2f1a29e7cc9a75a13b405deced3993ac052c812fbc2508da4964981c"},"schema_version":"1.0","source":{"id":"2506.03723","kind":"arxiv","version":1}},"canonical_sha256":"7efaa5b2a981a7c0862e8be772e65f5001603d306b6c99c5e2f677eb1c521d27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7efaa5b2a981a7c0862e8be772e65f5001603d306b6c99c5e2f677eb1c521d27","first_computed_at":"2026-07-05T11:15:50.761565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:50.761565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KeJ49awyeCS5My54ZhIUiz8FfJ58jXO3d5bhOfdn6MwbT33pPRTsP8v4jTJrj8e6taavaZPHCwPyq1Ee2hFkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:50.762065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca89c6bbb1b2eaf741ccaea27aa3266c6fd3a248a7e0cd0673ccca3a15ab9e7a","sha256:7e9d241c17c2343d49caba7f7f903c1f2bd3189273729fc48878f63f71822fc6"],"state_sha256":"996c53b513722947b2ca7c8878d3f44a2e3bedfe28f8cc380251197ebd4ed744"}