{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RMT5LNGGU6A52BWEOUOHPITZYZ","short_pith_number":"pith:RMT5LNGG","schema_version":"1.0","canonical_sha256":"8b27d5b4c6a781dd06c4751c77a279c6494cadbd1fd73d3a5ffad8a124cd3f38","source":{"kind":"arxiv","id":"2207.09957","version":1},"attestation_state":"computed","paper":{"title":"Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Glocker, Chen Chen, Konstantinos Kamnitsas, Mobarakol Islam, Zeju Li","submitted_at":"2022-07-20T15:04:32Z","abstract_excerpt":"Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift. If we could estimate the performance that a pre-trained model would achieve on data from a specific deployment setting, for example a certain clinic, we could judge whether the model could safely be deployed or if its performance degrades unacceptably on the specific data. Existing approaches estimate this based on the confidence of predictions made on unlabeled test data from the deployment's domain. We find existi"},"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":"2207.09957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T15:04:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5fa69682b8705c9dedd725f42f004c9e6d503dfe2d19868917a96fe7c43cf1e","abstract_canon_sha256":"93cfa7e397c055689724b55bd0b1fa7d2fd58f2c11bf942fc846f7f9deb88fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:03.769589Z","signature_b64":"UlvSVikqz2lIrbLaeQlda/MULhrag/QZRLl8i8zmNQNSaRWF8VJbAf6T3fag1ciGfuDk2U/QkHc+rRqlhZpfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b27d5b4c6a781dd06c4751c77a279c6494cadbd1fd73d3a5ffad8a124cd3f38","last_reissued_at":"2026-07-05T04:42:03.769159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:03.769159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Glocker, Chen Chen, Konstantinos Kamnitsas, Mobarakol Islam, Zeju Li","submitted_at":"2022-07-20T15:04:32Z","abstract_excerpt":"Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift. If we could estimate the performance that a pre-trained model would achieve on data from a specific deployment setting, for example a certain clinic, we could judge whether the model could safely be deployed or if its performance degrades unacceptably on the specific data. Existing approaches estimate this based on the confidence of predictions made on unlabeled test data from the deployment's domain. We find existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09957","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/2207.09957/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":"2207.09957","created_at":"2026-07-05T04:42:03.769214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09957v1","created_at":"2026-07-05T04:42:03.769214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09957","created_at":"2026-07-05T04:42:03.769214+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMT5LNGGU6A5","created_at":"2026-07-05T04:42:03.769214+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMT5LNGGU6A52BWE","created_at":"2026-07-05T04:42:03.769214+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMT5LNGG","created_at":"2026-07-05T04:42:03.769214+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/RMT5LNGGU6A52BWEOUOHPITZYZ","json":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ.json","graph_json":"https://pith.science/api/pith-number/RMT5LNGGU6A52BWEOUOHPITZYZ/graph.json","events_json":"https://pith.science/api/pith-number/RMT5LNGGU6A52BWEOUOHPITZYZ/events.json","paper":"https://pith.science/paper/RMT5LNGG"},"agent_actions":{"view_html":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ","download_json":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ.json","view_paper":"https://pith.science/paper/RMT5LNGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09957&json=true","fetch_graph":"https://pith.science/api/pith-number/RMT5LNGGU6A52BWEOUOHPITZYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RMT5LNGGU6A52BWEOUOHPITZYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ/action/storage_attestation","attest_author":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ/action/author_attestation","sign_citation":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ/action/citation_signature","submit_replication":"https://pith.science/pith/RMT5LNGGU6A52BWEOUOHPITZYZ/action/replication_record"}},"created_at":"2026-07-05T04:42:03.769214+00:00","updated_at":"2026-07-05T04:42:03.769214+00:00"}