{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:APTRUL4LNM7VUU2DTPUUNONQYQ","short_pith_number":"pith:APTRUL4L","schema_version":"1.0","canonical_sha256":"03e71a2f8b6b3f5a53439be946b9b0c406e2c5d3ccac9740a5388386dcfe91ee","source":{"kind":"arxiv","id":"2110.02459","version":1},"attestation_state":"computed","paper":{"title":"Post-hoc Models for Performance Estimation of Machine Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiasi Chen, Samet Oymak, Xuechen Zhang","submitted_at":"2021-10-06T02:20:37Z","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. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.02459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-06T02:20:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60d031fba3a9e968d2301342f451492d26023f8493c8516825d1d2f3fb7f7a6d","abstract_canon_sha256":"2f472fc9bd8b6648a9980a8545b17a1612de380006a3879536fd2288cfca1f77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:26.391908Z","signature_b64":"a5bhwubkon7IcMSQ5Q7dhJxs77OGxQLGfBY6WlPxFvd6iEuFiogQL+Py2OsSjnMEfFtLWBtGBobTUsaCK4opBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e71a2f8b6b3f5a53439be946b9b0c406e2c5d3ccac9740a5388386dcfe91ee","last_reissued_at":"2026-07-05T03:20:26.391560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:26.391560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-hoc Models for Performance Estimation of Machine Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiasi Chen, Samet Oymak, Xuechen Zhang","submitted_at":"2021-10-06T02:20:37Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02459","kind":"arxiv","version":1},"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/2110.02459/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.02459","created_at":"2026-07-05T03:20:26.391622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02459v1","created_at":"2026-07-05T03:20:26.391622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02459","created_at":"2026-07-05T03:20:26.391622+00:00"},{"alias_kind":"pith_short_12","alias_value":"APTRUL4LNM7V","created_at":"2026-07-05T03:20:26.391622+00:00"},{"alias_kind":"pith_short_16","alias_value":"APTRUL4LNM7VUU2D","created_at":"2026-07-05T03:20:26.391622+00:00"},{"alias_kind":"pith_short_8","alias_value":"APTRUL4L","created_at":"2026-07-05T03:20:26.391622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ","json":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ.json","graph_json":"https://pith.science/api/pith-number/APTRUL4LNM7VUU2DTPUUNONQYQ/graph.json","events_json":"https://pith.science/api/pith-number/APTRUL4LNM7VUU2DTPUUNONQYQ/events.json","paper":"https://pith.science/paper/APTRUL4L"},"agent_actions":{"view_html":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ","download_json":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ.json","view_paper":"https://pith.science/paper/APTRUL4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02459&json=true","fetch_graph":"https://pith.science/api/pith-number/APTRUL4LNM7VUU2DTPUUNONQYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/APTRUL4LNM7VUU2DTPUUNONQYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ/action/storage_attestation","attest_author":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ/action/author_attestation","sign_citation":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ/action/citation_signature","submit_replication":"https://pith.science/pith/APTRUL4LNM7VUU2DTPUUNONQYQ/action/replication_record"}},"created_at":"2026-07-05T03:20:26.391622+00:00","updated_at":"2026-07-05T03:20:26.391622+00:00"}