{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PDMZDH2FBCRTB4XE5C7DNCSTPH","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":"7102d3054971ca175c6e7b79059ca70dc99f9faefe2db87138b0da4da5ba0511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T19:50:02Z","title_canon_sha256":"64aab1051a8ed5d062bfd9eb3a85b159943f9d08687ddcef1946db5600c3bb38"},"schema_version":"1.0","source":{"id":"2510.05126","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05126","created_at":"2026-06-23T01:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05126v3","created_at":"2026-06-23T01:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05126","created_at":"2026-06-23T01:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"PDMZDH2FBCRT","created_at":"2026-06-23T01:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"PDMZDH2FBCRTB4XE","created_at":"2026-06-23T01:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"PDMZDH2F","created_at":"2026-06-23T01:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:9fe6ab1043ea4e428514ca959cec76e809b29cbc79767ff9bc827b9a47dd8afb","target":"graph","created_at":"2026-06-23T01:11:57Z","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/2510.05126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background. Large language models are increasingly used in settings where confident but incorrect answers can mislead users. Reliable uncertainty communication requires a form of metacognition: monitoring when one's own answers are likely to be correct. Yet models' stated confidence is often poorly aligned with answer correctness. We test whether supervised fine-tuning improves uncertainty communication and whether gains transfer across domains and task formats.\n  Methods. We fine-tuned two models on general knowledge, mathematics, and open-ended trivia questions. We evaluated single-question ","authors_text":"Catarina Belem, Mark Steyvers, Padhraic Smyth","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T19:50:02Z","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05126","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:f81ed4f00117dce9f370a788b8f7f7621cefe9cab19987837d47b9f21c9392c4","target":"record","created_at":"2026-06-23T01:11:57Z","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":"7102d3054971ca175c6e7b79059ca70dc99f9faefe2db87138b0da4da5ba0511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T19:50:02Z","title_canon_sha256":"64aab1051a8ed5d062bfd9eb3a85b159943f9d08687ddcef1946db5600c3bb38"},"schema_version":"1.0","source":{"id":"2510.05126","kind":"arxiv","version":3}},"canonical_sha256":"78d9919f4508a330f2e4e8be368a5379d76c85f72243b9175a94f1bc3133c851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78d9919f4508a330f2e4e8be368a5379d76c85f72243b9175a94f1bc3133c851","first_computed_at":"2026-06-23T01:11:57.671931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:11:57.671931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S1Xi5yq/KjHVgR9u7lYQcbviZjwY9bSi6gnDLelHOfxs3P7Q21WdonmhItEWmBQHTHXLQkjaxqbV9BdmUIDODw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:11:57.672415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05126","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f81ed4f00117dce9f370a788b8f7f7621cefe9cab19987837d47b9f21c9392c4","sha256:9fe6ab1043ea4e428514ca959cec76e809b29cbc79767ff9bc827b9a47dd8afb"],"state_sha256":"3e6b76dd99bd3d1535219ac08d9357dcef34bbac5d54b8ef881294d0cb75a15e"}