{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6U4M2BEUB23OBT4FQBEQ2TMDVG","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":"a447861236afe05c07d77ae3b9e54bebc4dab835b4b2f827927ef1b816410eea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T18:48:42Z","title_canon_sha256":"6adcf50bbb99bf7d53a3a972f77564b96d3e83312a6318edf7680840c4bcc34b"},"schema_version":"1.0","source":{"id":"2501.03991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03991","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03991v1","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03991","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"6U4M2BEUB23O","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_16","alias_value":"6U4M2BEUB23OBT4F","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_8","alias_value":"6U4M2BEU","created_at":"2026-07-05T09:58:14Z"}],"graph_snapshots":[{"event_id":"sha256:1bb7673caeec9d68d328fe9546f05681170992022e25f823b0a75756ede01ae6","target":"graph","created_at":"2026-07-05T09:58:14Z","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/2501.03991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Calibration, the alignment between model confidence and prediction accuracy, is critical for the reliable deployment of large language models (LLMs). Existing works neglect to measure the generalization of their methods to other prompt styles and different sizes of LLMs. To address this, we define a controlled experimental setting covering 12 LLMs and four prompt styles. We additionally investigate if incorporating the response agreement of multiple LLMs and an appropriate loss function can improve calibration performance. Concretely, we build Calib-n, a novel framework that trains an auxiliar","authors_text":"Benjamin Roth, Klim Zaporojets, Pedro Henrique Luz de Araujo, Yuxi Xia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T18:48:42Z","title":"Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03991","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:db8cfd2c47dddaa0bb63d0092f384fd59f21d3ed0206c2291266fc1818b20e4b","target":"record","created_at":"2026-07-05T09:58:14Z","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":"a447861236afe05c07d77ae3b9e54bebc4dab835b4b2f827927ef1b816410eea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T18:48:42Z","title_canon_sha256":"6adcf50bbb99bf7d53a3a972f77564b96d3e83312a6318edf7680840c4bcc34b"},"schema_version":"1.0","source":{"id":"2501.03991","kind":"arxiv","version":1}},"canonical_sha256":"f538cd04940eb6e0cf8580490d4d83a9a234dce12ac41c26c7a4fbbe09a34212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f538cd04940eb6e0cf8580490d4d83a9a234dce12ac41c26c7a4fbbe09a34212","first_computed_at":"2026-07-05T09:58:14.042478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:14.042478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFIEptl41FUUAnRqraGr4X+j+DZ3E/34EwhrE0E+z51pu+gVOOLESo4oKkKk7mtxVTOygd0QBQU39MvepIYFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:14.042899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db8cfd2c47dddaa0bb63d0092f384fd59f21d3ed0206c2291266fc1818b20e4b","sha256:1bb7673caeec9d68d328fe9546f05681170992022e25f823b0a75756ede01ae6"],"state_sha256":"35a2a664915173a66eaa06abd27cdef09c9b6bf6c82b1a099f1b36644e1d0673"}