{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3NE2AKE4THNB3HS4HJK2ZUANWP","short_pith_number":"pith:3NE2AKE4","schema_version":"1.0","canonical_sha256":"db49a0289c99da1d9e5c3a55acd00db3fae5be7bcbf306acb8efa403a2231304","source":{"kind":"arxiv","id":"2606.21937","version":1},"attestation_state":"computed","paper":{"title":"Latent Confidence Alignment for LLM Self-Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Chan Hsu, Ming-Yen Lin, Pei-Cing Huang, Tingting Yu, Ting-Yu Chen, Yihuang Kang","submitted_at":"2026-06-20T08:13:31Z","abstract_excerpt":"Confidence calibration in large language models (LLMs) is commonly evaluated by comparing predicted confidence with observed accuracy. However, such approaches do not model item difficulty, making it difficult to interpret discrepancies and to determine whether model confidence reflects genuine self-assessment or is merely a byproduct of the response generation process. To address this, we adopt a Rasch model-based latent ability framework and a metacognitive perspective, and propose Latent Confidence Alignment Error (LCAE) to measure the consistency between model self-assessment and the laten"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.21937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2026-06-20T08:13:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"52f2fb1ba53943be8d5105b18393a543d183ebe37a6c72a637516fa340664b26","abstract_canon_sha256":"364e7557923900ae3cfe340e06b47dc08d4787d459cb868e7b7c1f4acdbdfde0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:03.571203Z","signature_b64":"/zbW+cNu1llQ43V4OkZdSpKKKvs7K94yy0CYMjJZREsqcJekSBzt+hK5HdwiNyP6bnbAJpOMNP9OpHsgyV3NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db49a0289c99da1d9e5c3a55acd00db3fae5be7bcbf306acb8efa403a2231304","last_reissued_at":"2026-06-23T02:13:03.570792Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:03.570792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Confidence Alignment for LLM Self-Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Chan Hsu, Ming-Yen Lin, Pei-Cing Huang, Tingting Yu, Ting-Yu Chen, Yihuang Kang","submitted_at":"2026-06-20T08:13:31Z","abstract_excerpt":"Confidence calibration in large language models (LLMs) is commonly evaluated by comparing predicted confidence with observed accuracy. However, such approaches do not model item difficulty, making it difficult to interpret discrepancies and to determine whether model confidence reflects genuine self-assessment or is merely a byproduct of the response generation process. To address this, we adopt a Rasch model-based latent ability framework and a metacognitive perspective, and propose Latent Confidence Alignment Error (LCAE) to measure the consistency between model self-assessment and the laten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21937","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.21937/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.21937","created_at":"2026-06-23T02:13:03.570843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21937v1","created_at":"2026-06-23T02:13:03.570843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21937","created_at":"2026-06-23T02:13:03.570843+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NE2AKE4THNB","created_at":"2026-06-23T02:13:03.570843+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NE2AKE4THNB3HS4","created_at":"2026-06-23T02:13:03.570843+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NE2AKE4","created_at":"2026-06-23T02:13:03.570843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP","json":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP.json","graph_json":"https://pith.science/api/pith-number/3NE2AKE4THNB3HS4HJK2ZUANWP/graph.json","events_json":"https://pith.science/api/pith-number/3NE2AKE4THNB3HS4HJK2ZUANWP/events.json","paper":"https://pith.science/paper/3NE2AKE4"},"agent_actions":{"view_html":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP","download_json":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP.json","view_paper":"https://pith.science/paper/3NE2AKE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21937&json=true","fetch_graph":"https://pith.science/api/pith-number/3NE2AKE4THNB3HS4HJK2ZUANWP/graph.json","fetch_events":"https://pith.science/api/pith-number/3NE2AKE4THNB3HS4HJK2ZUANWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP/action/storage_attestation","attest_author":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP/action/author_attestation","sign_citation":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP/action/citation_signature","submit_replication":"https://pith.science/pith/3NE2AKE4THNB3HS4HJK2ZUANWP/action/replication_record"}},"created_at":"2026-06-23T02:13:03.570843+00:00","updated_at":"2026-06-23T02:13:03.570843+00:00"}