{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K2YZJN2U6ZLNQGH6NGRWOLLK5U","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":"92e2b51876eb8b141161dfb9d091eb21a04c9b10eb323bf6ccc804b60e52144e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-18T15:31:43Z","title_canon_sha256":"0b4ff1b7d12e9cc61f35d8fcb6f981bc9f6f6a3d78372f8579acbc9abecf4e3f"},"schema_version":"1.0","source":{"id":"2603.17839","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.17839","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2603.17839v3","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17839","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"K2YZJN2U6ZLN","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"K2YZJN2U6ZLNQGH6","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"K2YZJN2U","created_at":"2026-05-20T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:877bdc10080aac8fe01f8bac2a4cac4335496e373e0ee390e3eb08b57d8e5cd3","target":"graph","created_at":"2026-05-20T01:05:11Z","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/2603.17839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed -- just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents -- token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B (across TriviaQA, BigMath, and MMLU), Qwen 2.5 7B, and the reasoni","authors_text":"Arthur Conmy, Dharshan Kumaran, Federico Barbero, Petar Veli\\v{c}kovi\\'c, Simon Osindero, Viorica Patraucean","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-18T15:31:43Z","title":"How do LLMs Compute Verbal Confidence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17839","kind":"arxiv","version":3},"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":"sha256:63a021f9f50bf5744fa895a1234b81965e1c5482ff70526bba777d0aa24b7ef2","target":"record","created_at":"2026-05-20T01:05:11Z","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":"92e2b51876eb8b141161dfb9d091eb21a04c9b10eb323bf6ccc804b60e52144e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-18T15:31:43Z","title_canon_sha256":"0b4ff1b7d12e9cc61f35d8fcb6f981bc9f6f6a3d78372f8579acbc9abecf4e3f"},"schema_version":"1.0","source":{"id":"2603.17839","kind":"arxiv","version":3}},"canonical_sha256":"56b194b754f656d818fe69a3672d6aed0a210f8de391e093330c61f7b9bc1739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56b194b754f656d818fe69a3672d6aed0a210f8de391e093330c61f7b9bc1739","first_computed_at":"2026-05-20T01:05:11.400901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:11.400901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ikJxZIfN2+W3DkYwhnyFLQhKAlOw36lnfqucsI2nrwjzvDEHg3mVSO/pjnM/Rz2+mDUMxU+MaT0UF/3KBEJiDw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:11.401669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.17839","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63a021f9f50bf5744fa895a1234b81965e1c5482ff70526bba777d0aa24b7ef2","sha256:877bdc10080aac8fe01f8bac2a4cac4335496e373e0ee390e3eb08b57d8e5cd3"],"state_sha256":"7becc94c6ff3551edc3c72777255982ea9cf9b5a9627842d840c3a051c565eb5"}