{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K7G5MXICRSDS5BYPCYI44KXSJT","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":"a9eed09ab741d2d32765add25e49e5b09d49feb34732c8a4b36d326e3df68ee3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T03:37:39Z","title_canon_sha256":"58e7b51fb683283f872123f6eced14db670631263453ba7ec5599825666f04c2"},"schema_version":"1.0","source":{"id":"2312.04021","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04021","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04021v4","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04021","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"K7G5MXICRSDS","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"K7G5MXICRSDS5BYP","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"K7G5MXIC","created_at":"2026-07-05T08:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:ea14e1072c4284f52cd6953aaa6bc6b2083108386f39d93f1f89029c940ca4e9","target":"graph","created_at":"2026-07-05T08:01:35Z","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/2312.04021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a prevalent method for adapting static LMs through tailored prompts, and examine the balance between performance and calibration across a broad spectrum of natural language understanding and reasoning tasks. Through comprehensive experiments, we observe that, with an increasing number of ICL examples, models initially exhibit increased miscalibration before achi","authors_text":"Dean Foster, Dhruv Madeka, Eric Xing, Hanlin Zhang, Himabindu Lakkaraju, Sham Kakade, Yaodong Yu, Yi-Fan Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T03:37:39Z","title":"A Study on the Calibration of In-context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04021","kind":"arxiv","version":4},"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":"sha256:487614d0d48ec2aeb0a8184cdf5994f0efdba0652fec1799098330cb13bfbfbb","target":"record","created_at":"2026-07-05T08:01:35Z","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":"a9eed09ab741d2d32765add25e49e5b09d49feb34732c8a4b36d326e3df68ee3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T03:37:39Z","title_canon_sha256":"58e7b51fb683283f872123f6eced14db670631263453ba7ec5599825666f04c2"},"schema_version":"1.0","source":{"id":"2312.04021","kind":"arxiv","version":4}},"canonical_sha256":"57cdd65d028c872e870f1611ce2af24cf8ea6f9cfd1aee6a0ccf19b1f641a523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57cdd65d028c872e870f1611ce2af24cf8ea6f9cfd1aee6a0ccf19b1f641a523","first_computed_at":"2026-07-05T08:01:35.625911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:35.625911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fOEJaCPrkv6pnZGqVNAmHjpl/xomNjE0VVQbHEFKgUxsCTrNQr2uUp4oDSc1EF8FXNsAgHh7ghoNE4PUyJAXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:35.626472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04021","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:487614d0d48ec2aeb0a8184cdf5994f0efdba0652fec1799098330cb13bfbfbb","sha256:ea14e1072c4284f52cd6953aaa6bc6b2083108386f39d93f1f89029c940ca4e9"],"state_sha256":"dc77faa1e98dc7f0637339ce45291fb7283508c42946aa11e96a406a6538717f"}