{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WM7QNTATP77YUZKPCXLJGHQCVJ","short_pith_number":"pith:WM7QNTAT","canonical_record":{"source":{"id":"2310.11732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T06:07:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34122d2e7d5df83020eb1ad019b03405d0ec8aae16b668a9525a7b73097e7228","abstract_canon_sha256":"0d67ae21b38cfbf1c77af71a9f4f724f92dcb7b006bf0c6ab3aa0722e199d94e"},"schema_version":"1.0"},"canonical_sha256":"b33f06cc137fff8a654f15d6931e02aa767798387c4c282e32fbc75f0aa7ac30","source":{"kind":"arxiv","id":"2310.11732","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11732","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11732v2","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11732","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"WM7QNTATP77Y","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"WM7QNTATP77YUZKP","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"WM7QNTAT","created_at":"2026-07-05T07:14:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WM7QNTATP77YUZKPCXLJGHQCVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T06:07:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34122d2e7d5df83020eb1ad019b03405d0ec8aae16b668a9525a7b73097e7228","abstract_canon_sha256":"0d67ae21b38cfbf1c77af71a9f4f724f92dcb7b006bf0c6ab3aa0722e199d94e"},"schema_version":"1.0"},"canonical_sha256":"b33f06cc137fff8a654f15d6931e02aa767798387c4c282e32fbc75f0aa7ac30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:19.118376Z","signature_b64":"FFF8spF6Yo9ym4LMS1EanotdPpW5YA5oLIewffCNmIUaQYGwmNkkTXClhjHbpSQ+HnvjjWmnCXonCNGVABcTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33f06cc137fff8a654f15d6931e02aa767798387c4c282e32fbc75f0aa7ac30","last_reissued_at":"2026-07-05T07:14:19.117714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:19.117714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11732","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BOij5jo/autleMzeaIQzXAtQVrQmKn31ayVjw0t19gyCu+R0hLHFq2jXuEixVUiTPAVSj11Doi69yzs2I/ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:15.846003Z"},"content_sha256":"1ac845296fb8867f23e1de87414016079682599a4485590f0ffde6bd81e9a114","schema_version":"1.0","event_id":"sha256:1ac845296fb8867f23e1de87414016079682599a4485590f0ffde6bd81e9a114"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WM7QNTATP77YUZKPCXLJGHQCVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guande He, Jianfei Chen, Jun Zhu, Peng Cui, Wenbo Hu","submitted_at":"2023-10-18T06:07:28Z","abstract_excerpt":"Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs. In this work, we systematically evaluate the impact of the alignment process on logit-based uncertainty calibration of LMs under the multiple-choice setting. We first conduct a thoughtful empirical study on how aligned LMs differ in calibration from their pre-trained counterparts. Experimental results reveal that there are two distinct uncertainties in LMs under the multiple-choice setting, which are res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11732","kind":"arxiv","version":2},"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/2310.11732/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJtFbhY4VLJ9Kc2TsEQrcXa8dQxQaer/vlzMhKAQbUwwvdK+pNRbrN8hWCQftsG60RIySvDYz8KQDE0CADJDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:15.846878Z"},"content_sha256":"21bbb2fbb42c06c00898a49cbe8cccb3838574b826ef0c181eb4a7f3437d7c34","schema_version":"1.0","event_id":"sha256:21bbb2fbb42c06c00898a49cbe8cccb3838574b826ef0c181eb4a7f3437d7c34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/bundle.json","state_url":"https://pith.science/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T14:14:15Z","links":{"resolver":"https://pith.science/pith/WM7QNTATP77YUZKPCXLJGHQCVJ","bundle":"https://pith.science/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/bundle.json","state":"https://pith.science/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WM7QNTATP77YUZKPCXLJGHQCVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WM7QNTATP77YUZKPCXLJGHQCVJ","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":"0d67ae21b38cfbf1c77af71a9f4f724f92dcb7b006bf0c6ab3aa0722e199d94e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T06:07:28Z","title_canon_sha256":"34122d2e7d5df83020eb1ad019b03405d0ec8aae16b668a9525a7b73097e7228"},"schema_version":"1.0","source":{"id":"2310.11732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11732","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11732v2","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11732","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"WM7QNTATP77Y","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"WM7QNTATP77YUZKP","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"WM7QNTAT","created_at":"2026-07-05T07:14:19Z"}],"graph_snapshots":[{"event_id":"sha256:21bbb2fbb42c06c00898a49cbe8cccb3838574b826ef0c181eb4a7f3437d7c34","target":"graph","created_at":"2026-07-05T07:14:19Z","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/2310.11732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs. In this work, we systematically evaluate the impact of the alignment process on logit-based uncertainty calibration of LMs under the multiple-choice setting. We first conduct a thoughtful empirical study on how aligned LMs differ in calibration from their pre-trained counterparts. Experimental results reveal that there are two distinct uncertainties in LMs under the multiple-choice setting, which are res","authors_text":"Guande He, Jianfei Chen, Jun Zhu, Peng Cui, Wenbo Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T06:07:28Z","title":"Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11732","kind":"arxiv","version":2},"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":"sha256:1ac845296fb8867f23e1de87414016079682599a4485590f0ffde6bd81e9a114","target":"record","created_at":"2026-07-05T07:14:19Z","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":"0d67ae21b38cfbf1c77af71a9f4f724f92dcb7b006bf0c6ab3aa0722e199d94e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T06:07:28Z","title_canon_sha256":"34122d2e7d5df83020eb1ad019b03405d0ec8aae16b668a9525a7b73097e7228"},"schema_version":"1.0","source":{"id":"2310.11732","kind":"arxiv","version":2}},"canonical_sha256":"b33f06cc137fff8a654f15d6931e02aa767798387c4c282e32fbc75f0aa7ac30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b33f06cc137fff8a654f15d6931e02aa767798387c4c282e32fbc75f0aa7ac30","first_computed_at":"2026-07-05T07:14:19.117714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:19.117714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FFF8spF6Yo9ym4LMS1EanotdPpW5YA5oLIewffCNmIUaQYGwmNkkTXClhjHbpSQ+HnvjjWmnCXonCNGVABcTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:19.118376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ac845296fb8867f23e1de87414016079682599a4485590f0ffde6bd81e9a114","sha256:21bbb2fbb42c06c00898a49cbe8cccb3838574b826ef0c181eb4a7f3437d7c34"],"state_sha256":"f6aa0929c199d13d482ab04936075f229f61d53fba0d40f241db062d7c9b0667"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vg0u/SW3tyurD9aZSeqPbcpNks2i8Zmc6sxRy+HBw0sIasyC+g1eGjtjqN2NNdks16tzMatnsgyOo8HwoSi2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:14:15.853794Z","bundle_sha256":"fa3c359ce44a9987147ff255e9ca7260be25f14d9513a4306aa5f19cb3c5ee62"}}