{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MFBPUAXANXMQICPLHVKNDNKCI3","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":"70b27e80f77dd9e93339e196754ce12d003ccc1a0089b827c3c036006e44505f","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T00:04:56Z","title_canon_sha256":"a9450cdb46a6e2a807f112a6c8d0c57c1026cbab616677ec1427a7e70a3a1a93"},"schema_version":"1.0","source":{"id":"2210.01964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01964","created_at":"2026-07-05T05:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01964v2","created_at":"2026-07-05T05:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01964","created_at":"2026-07-05T05:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"MFBPUAXANXMQ","created_at":"2026-07-05T05:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"MFBPUAXANXMQICPL","created_at":"2026-07-05T05:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"MFBPUAXA","created_at":"2026-07-05T05:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:abd48767630022b949a091c16474df478d9569e7b2c67a73e32c0449113b352f","target":"graph","created_at":"2026-07-05T05:03:52Z","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/2210.01964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Calibration is a fundamental property of a good predictive model: it requires that the model predicts correctly in proportion to its confidence. Modern neural networks, however, provide no strong guarantees on their calibration -- and can be either poorly calibrated or well-calibrated depending on the setting. It is currently unclear which factors contribute to good calibration (architecture, data augmentation, overparameterization, etc), though various claims exist in the literature.\n  We propose a systematic way to study the calibration error: by decomposing it into (1) calibration error on ","authors_text":"A. Michael Carrell, James Lucas, Neil Mallinar, Preetum Nakkiran","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T00:04:56Z","title":"The Calibration Generalization Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01964","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:f747ca10223c3deb9163cdf23b17c6309c4d9b70e147be58d3d8b84815f771da","target":"record","created_at":"2026-07-05T05:03:52Z","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":"70b27e80f77dd9e93339e196754ce12d003ccc1a0089b827c3c036006e44505f","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T00:04:56Z","title_canon_sha256":"a9450cdb46a6e2a807f112a6c8d0c57c1026cbab616677ec1427a7e70a3a1a93"},"schema_version":"1.0","source":{"id":"2210.01964","kind":"arxiv","version":2}},"canonical_sha256":"6142fa02e06dd90409eb3d54d1b54246c2b058a6563874272900e7f7a9d609d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6142fa02e06dd90409eb3d54d1b54246c2b058a6563874272900e7f7a9d609d3","first_computed_at":"2026-07-05T05:03:52.772074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:52.772074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNgfhZYJ0HH/O3oe4WMAV0Mm3AdWKapuxAVs/1nCes4Uue/Ss4JiZBbS+LNtzz3q1b36y1e360Rz5XMycY2KDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:52.772503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f747ca10223c3deb9163cdf23b17c6309c4d9b70e147be58d3d8b84815f771da","sha256:abd48767630022b949a091c16474df478d9569e7b2c67a73e32c0449113b352f"],"state_sha256":"419ac7f9e5f1a9742d78e1b4b5f896c2cc60447e9bd36d69693cb65f98914436"}