{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:APTRUL4LNM7VUU2DTPUUNONQYQ","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":"2f472fc9bd8b6648a9980a8545b17a1612de380006a3879536fd2288cfca1f77","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-06T02:20:37Z","title_canon_sha256":"60d031fba3a9e968d2301342f451492d26023f8493c8516825d1d2f3fb7f7a6d"},"schema_version":"1.0","source":{"id":"2110.02459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02459","created_at":"2026-07-05T03:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02459v1","created_at":"2026-07-05T03:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02459","created_at":"2026-07-05T03:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"APTRUL4LNM7V","created_at":"2026-07-05T03:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"APTRUL4LNM7VUU2D","created_at":"2026-07-05T03:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"APTRUL4L","created_at":"2026-07-05T03:20:26Z"}],"graph_snapshots":[{"event_id":"sha256:4ba153213004a273b420e089bc0dcb7e7df0d8e1c69d22a1c1d43805f66ce1ac","target":"graph","created_at":"2026-07-05T03:20:26Z","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/2110.02459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimating how well a machine learning model performs during inference is critical in a variety of scenarios (for example, to quantify uncertainty, or to choose from a library of available models). However, the standard accuracy estimate of softmax confidence is not versatile and cannot reliably predict different performance metrics (e.g., F1-score, recall) or the performance in different application scenarios or input domains. In this work, we systematically generalize performance estimation to a diverse set of metrics and scenarios and discuss generalized notions of uncertainty calibration. ","authors_text":"Jiasi Chen, Samet Oymak, Xuechen Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-06T02:20:37Z","title":"Post-hoc Models for Performance Estimation of Machine Learning Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02459","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":"sha256:3c1b6c674ccd2d29813e6dbb270ad7700342f6ce7a2ec358ffa21808e8c1f79f","target":"record","created_at":"2026-07-05T03:20:26Z","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":"2f472fc9bd8b6648a9980a8545b17a1612de380006a3879536fd2288cfca1f77","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-06T02:20:37Z","title_canon_sha256":"60d031fba3a9e968d2301342f451492d26023f8493c8516825d1d2f3fb7f7a6d"},"schema_version":"1.0","source":{"id":"2110.02459","kind":"arxiv","version":1}},"canonical_sha256":"03e71a2f8b6b3f5a53439be946b9b0c406e2c5d3ccac9740a5388386dcfe91ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e71a2f8b6b3f5a53439be946b9b0c406e2c5d3ccac9740a5388386dcfe91ee","first_computed_at":"2026-07-05T03:20:26.391560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:26.391560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5bhwubkon7IcMSQ5Q7dhJxs77OGxQLGfBY6WlPxFvd6iEuFiogQL+Py2OsSjnMEfFtLWBtGBobTUsaCK4opBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:26.391908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c1b6c674ccd2d29813e6dbb270ad7700342f6ce7a2ec358ffa21808e8c1f79f","sha256:4ba153213004a273b420e089bc0dcb7e7df0d8e1c69d22a1c1d43805f66ce1ac"],"state_sha256":"06d8520e49f60a746b052b7bdd4a9790d8bf4bd17dc7a1aacde6c5bfc17b6176"}