{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RT4RGK54JKRLM3MHR4ECR4XBQG","short_pith_number":"pith:RT4RGK54","canonical_record":{"source":{"id":"2205.12507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T05:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"44e42cc6dc89e5b3101457fd9d88cc631c6e3e14e49a3b7c58a0944a43cff459","abstract_canon_sha256":"1d0985e04773c4c26d47598e50aff894d3f2af337a3d3963501fb49760a2a2d4"},"schema_version":"1.0"},"canonical_sha256":"8cf9132bbc4aa2b66d878f0828f2e181af8251bf225b95fae39411cd6d7c8364","source":{"kind":"arxiv","id":"2205.12507","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12507","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12507v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12507","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"RT4RGK54JKRL","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"RT4RGK54JKRLM3MH","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"RT4RGK54","created_at":"2026-07-05T05:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RT4RGK54JKRLM3MHR4ECR4XBQG","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T05:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"44e42cc6dc89e5b3101457fd9d88cc631c6e3e14e49a3b7c58a0944a43cff459","abstract_canon_sha256":"1d0985e04773c4c26d47598e50aff894d3f2af337a3d3963501fb49760a2a2d4"},"schema_version":"1.0"},"canonical_sha256":"8cf9132bbc4aa2b66d878f0828f2e181af8251bf225b95fae39411cd6d7c8364","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:18.577927Z","signature_b64":"VEjFiAhE4sORVwdUifgxjfQgLW7ihDRdU7XNDMlL+uSNqNsVr02cBpoI+AugbE1skXiK6h5Rvh8H3IJzL+NTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf9132bbc4aa2b66d878f0828f2e181af8251bf225b95fae39411cd6d7c8364","last_reissued_at":"2026-07-05T05:09:18.577520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:18.577520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12507","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":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OjAK3D3cZeidSH9lRmyTN3sa3oeHH2OP1lDg1nC9IBf/AZ/iaWYHmtQDZ5H4Ye+ZhdAQnvliGpSIsfHHogXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T01:31:22.671502Z"},"content_sha256":"de0550d1564fbdbf019b81c492f26134e604346ace537057cab33e9be0129408","schema_version":"1.0","event_id":"sha256:de0550d1564fbdbf019b81c492f26134e604346ace537057cab33e9be0129408"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RT4RGK54JKRLM3MHR4ECR4XBQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Re-Examining Calibration: The Case of Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Chen Zhao, Jordan Boyd-Graber, Sewon Min","submitted_at":"2022-05-25T05:49:56Z","abstract_excerpt":"For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12507","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/2205.12507/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":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZKc7RKTpAPcsmMzcoF7i6dD4a8De6v0asl/COO530MF7Zsdb9hWGKNmEn81SFbOp4mAz6uDXecgwzho3C+0XAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T01:31:22.671877Z"},"content_sha256":"639cc02d0ce079fc5a8f77911addcc12cf68579cef8b56d295b40204783df602","schema_version":"1.0","event_id":"sha256:639cc02d0ce079fc5a8f77911addcc12cf68579cef8b56d295b40204783df602"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/bundle.json","state_url":"https://pith.science/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/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":"2026-07-21T01:31:22Z","links":{"resolver":"https://pith.science/pith/RT4RGK54JKRLM3MHR4ECR4XBQG","bundle":"https://pith.science/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/bundle.json","state":"https://pith.science/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RT4RGK54JKRLM3MHR4ECR4XBQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RT4RGK54JKRLM3MHR4ECR4XBQG","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":"1d0985e04773c4c26d47598e50aff894d3f2af337a3d3963501fb49760a2a2d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T05:49:56Z","title_canon_sha256":"44e42cc6dc89e5b3101457fd9d88cc631c6e3e14e49a3b7c58a0944a43cff459"},"schema_version":"1.0","source":{"id":"2205.12507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12507","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12507v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12507","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"RT4RGK54JKRL","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"RT4RGK54JKRLM3MH","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"RT4RGK54","created_at":"2026-07-05T05:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:639cc02d0ce079fc5a8f77911addcc12cf68579cef8b56d295b40204783df602","target":"graph","created_at":"2026-07-05T05:09:18Z","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/2205.12507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence t","authors_text":"Chenglei Si, Chen Zhao, Jordan Boyd-Graber, Sewon Min","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T05:49:56Z","title":"Re-Examining Calibration: The Case of Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12507","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:de0550d1564fbdbf019b81c492f26134e604346ace537057cab33e9be0129408","target":"record","created_at":"2026-07-05T05:09:18Z","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":"1d0985e04773c4c26d47598e50aff894d3f2af337a3d3963501fb49760a2a2d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T05:49:56Z","title_canon_sha256":"44e42cc6dc89e5b3101457fd9d88cc631c6e3e14e49a3b7c58a0944a43cff459"},"schema_version":"1.0","source":{"id":"2205.12507","kind":"arxiv","version":2}},"canonical_sha256":"8cf9132bbc4aa2b66d878f0828f2e181af8251bf225b95fae39411cd6d7c8364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cf9132bbc4aa2b66d878f0828f2e181af8251bf225b95fae39411cd6d7c8364","first_computed_at":"2026-07-05T05:09:18.577520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:18.577520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VEjFiAhE4sORVwdUifgxjfQgLW7ihDRdU7XNDMlL+uSNqNsVr02cBpoI+AugbE1skXiK6h5Rvh8H3IJzL+NTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:18.577927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de0550d1564fbdbf019b81c492f26134e604346ace537057cab33e9be0129408","sha256:639cc02d0ce079fc5a8f77911addcc12cf68579cef8b56d295b40204783df602"],"state_sha256":"32740fae6b2484f22329db2405b7bde4119ff380cf89163cc147a37b657f365e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xM1iPt02yatttadVle44ybSxu73dEiIRZQtDiu5qXUGFYTfXKtuHyhPrkXimfCZY9kMPHdx1LjgSMVUEjAoDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T01:31:22.674497Z","bundle_sha256":"9f4ea1aa97dcde75e516570930bd7a4747dbde086b83622ce4c948541191cec5"}}