{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOX4YT737WTZWNW574KIAISSWG","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":"219edb74e0f0367b2251cefe93980a891a9f4121fc08b066db0a4b7d8a9e7b6a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T01:51:45Z","title_canon_sha256":"b4b04a00f193ec5242173e358ce8c82b473316a0eb9b57fbe2994d23b071870a"},"schema_version":"1.0","source":{"id":"2502.19684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19684","created_at":"2026-07-05T10:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19684v1","created_at":"2026-07-05T10:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19684","created_at":"2026-07-05T10:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"UOX4YT737WTZ","created_at":"2026-07-05T10:20:50Z"},{"alias_kind":"pith_short_16","alias_value":"UOX4YT737WTZWNW5","created_at":"2026-07-05T10:20:50Z"},{"alias_kind":"pith_short_8","alias_value":"UOX4YT73","created_at":"2026-07-05T10:20:50Z"}],"graph_snapshots":[{"event_id":"sha256:fc6de3df9910eb026df9ee968adb7c696a5eecc8ee6b2d6dab5777ef2faea7df","target":"graph","created_at":"2026-07-05T10:20:50Z","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/2502.19684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are often miscalibrated, leading to confidently incorrect answers. We introduce GRACE, a benchmark for language model calibration that incorporates comparison with human calibration. GRACE consists of question-answer pairs, in which each question contains a series of clues that gradually become easier, all leading to the same answer; models must answer correctly as early as possible as the clues are revealed. This setting permits granular measurement of model calibration based on how early, accurately, and confidently a model answers. After collecting these questions, we host l","authors_text":"Eve Fleisig, Ishan Upadhyay, Jordan Lee Boyd-Graber, Yoo Yeon Sung, Yu Hou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T01:51:45Z","title":"GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19684","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:c2efc2e48121bfa0fe17be0cd1b39742bba7c809c5ca1c97dd81a5f69feae0f6","target":"record","created_at":"2026-07-05T10:20:50Z","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":"219edb74e0f0367b2251cefe93980a891a9f4121fc08b066db0a4b7d8a9e7b6a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T01:51:45Z","title_canon_sha256":"b4b04a00f193ec5242173e358ce8c82b473316a0eb9b57fbe2994d23b071870a"},"schema_version":"1.0","source":{"id":"2502.19684","kind":"arxiv","version":1}},"canonical_sha256":"a3afcc4ffbfda79b36ddff14802252b19c7167a9b5cf8cd0b4b8aae6793081fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3afcc4ffbfda79b36ddff14802252b19c7167a9b5cf8cd0b4b8aae6793081fe","first_computed_at":"2026-07-05T10:20:50.981026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:50.981026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tZnOehGy3sFgSfTKNW7X2KIKHIr1FuLrYwcWx56xgY6HEkoGnLQXolJf8KxZ/afkTCZcmRaX54w3ojtU+ZBjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:50.981717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2efc2e48121bfa0fe17be0cd1b39742bba7c809c5ca1c97dd81a5f69feae0f6","sha256:fc6de3df9910eb026df9ee968adb7c696a5eecc8ee6b2d6dab5777ef2faea7df"],"state_sha256":"1fdee9e017a673692f3ff30ed1607768d7137d6d497cd7ff184d4244d4d0cb25"}