{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:344HISZRGFGLPP3YI4M2OD5PIA","short_pith_number":"pith:344HISZR","schema_version":"1.0","canonical_sha256":"df38744b31314cb7bf784719a70faf403674541fd2de2e4aa80d0dae179364b6","source":{"kind":"arxiv","id":"2507.22776","version":1},"attestation_state":"computed","paper":{"title":"Label-free estimation of clinically relevant performance metrics under distribution shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alceu Bissoto, Lisa M. Koch, Tim Fl\\\"uhmann, Trung-Dung Hoang","submitted_at":"2025-07-30T15:37:58Z","abstract_excerpt":"Performance monitoring is essential for safe clinical deployment of image classification models. However, because ground-truth labels are typically unavailable in the target dataset, direct assessment of real-world model performance is infeasible. State-of-the-art performance estimation methods address this by leveraging confidence scores to estimate the target accuracy. Despite being a promising direction, the established methods mainly estimate the model's accuracy and are rarely evaluated in a clinical domain, where strong class imbalances and dataset shifts are common. Our contributions ar"},"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":"2507.22776","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"054a4ca13a0f2da7c3070420f2a5584c252e988b2ab876a60e9a584ee5f016de","abstract_canon_sha256":"6d5869f7f32540210321aec89a0de8a35a8b140f014d21be1b7325e9ab274049"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:48.962953Z","signature_b64":"ceoTiFXBqgiPATFGHdwakqkgh0s4WRSaB8tpZuSAe+oqkrUOvjg9a/mrELZlp3ZAz7MGR3U8mWaBDNUyKsuHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df38744b31314cb7bf784719a70faf403674541fd2de2e4aa80d0dae179364b6","last_reissued_at":"2026-07-05T11:45:48.962411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:48.962411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-free estimation of clinically relevant performance metrics under distribution shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alceu Bissoto, Lisa M. Koch, Tim Fl\\\"uhmann, Trung-Dung Hoang","submitted_at":"2025-07-30T15:37:58Z","abstract_excerpt":"Performance monitoring is essential for safe clinical deployment of image classification models. However, because ground-truth labels are typically unavailable in the target dataset, direct assessment of real-world model performance is infeasible. State-of-the-art performance estimation methods address this by leveraging confidence scores to estimate the target accuracy. Despite being a promising direction, the established methods mainly estimate the model's accuracy and are rarely evaluated in a clinical domain, where strong class imbalances and dataset shifts are common. Our contributions ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22776","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/2507.22776/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":"2507.22776","created_at":"2026-07-05T11:45:48.962469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22776v1","created_at":"2026-07-05T11:45:48.962469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22776","created_at":"2026-07-05T11:45:48.962469+00:00"},{"alias_kind":"pith_short_12","alias_value":"344HISZRGFGL","created_at":"2026-07-05T11:45:48.962469+00:00"},{"alias_kind":"pith_short_16","alias_value":"344HISZRGFGLPP3Y","created_at":"2026-07-05T11:45:48.962469+00:00"},{"alias_kind":"pith_short_8","alias_value":"344HISZR","created_at":"2026-07-05T11:45:48.962469+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/344HISZRGFGLPP3YI4M2OD5PIA","json":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA.json","graph_json":"https://pith.science/api/pith-number/344HISZRGFGLPP3YI4M2OD5PIA/graph.json","events_json":"https://pith.science/api/pith-number/344HISZRGFGLPP3YI4M2OD5PIA/events.json","paper":"https://pith.science/paper/344HISZR"},"agent_actions":{"view_html":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA","download_json":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA.json","view_paper":"https://pith.science/paper/344HISZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22776&json=true","fetch_graph":"https://pith.science/api/pith-number/344HISZRGFGLPP3YI4M2OD5PIA/graph.json","fetch_events":"https://pith.science/api/pith-number/344HISZRGFGLPP3YI4M2OD5PIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA/action/storage_attestation","attest_author":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA/action/author_attestation","sign_citation":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA/action/citation_signature","submit_replication":"https://pith.science/pith/344HISZRGFGLPP3YI4M2OD5PIA/action/replication_record"}},"created_at":"2026-07-05T11:45:48.962469+00:00","updated_at":"2026-07-05T11:45:48.962469+00:00"}