{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:WBY2SO75IZM4IVY2ZBOTRKJUS7","short_pith_number":"pith:WBY2SO75","schema_version":"1.0","canonical_sha256":"b071a93bfd4659c4571ac85d38a93497e03279efc868f8ef871636717224ecaa","source":{"kind":"arxiv","id":"1210.2162","version":1},"attestation_state":"computed","paper":{"title":"Semisupervised Classifier Evaluation and Recalibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Max Welling, Peter Welinder, Pietro Perona","submitted_at":"2012-10-08T07:15:57Z","abstract_excerpt":"How many labeled examples are needed to estimate a classifier's performance on a new dataset? We study the case where data is plentiful, but labels are expensive. We show that by making a few reasonable assumptions on the structure of the data, it is possible to estimate performance curves, with confidence bounds, using a small number of ground truth labels. Our approach, which we call Semisupervised Performance Evaluation (SPE), is based on a generative model for the classifier's confidence scores. In addition to estimating the performance of classifiers on new datasets, SPE can be used to re"},"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":"1210.2162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T07:15:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e6fdcca697de26786f13d5cb090357df2eb0f7e2035accf2b6ef16afa916ea18","abstract_canon_sha256":"38aa54ba8dd07f465e4862cd9c32774bb93cbf9f6497965f7df322e6f1e0450b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:43:50.923148Z","signature_b64":"7s3qTdls9I9dxdfOebgBovRKervO7Pb/rbuyJdB583pfbYZbsLn8Gld7THLUk+LleYY9Ri8rHIPO1FEGmmf5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b071a93bfd4659c4571ac85d38a93497e03279efc868f8ef871636717224ecaa","last_reissued_at":"2026-05-18T03:43:50.922675Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:43:50.922675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semisupervised Classifier Evaluation and Recalibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Max Welling, Peter Welinder, Pietro Perona","submitted_at":"2012-10-08T07:15:57Z","abstract_excerpt":"How many labeled examples are needed to estimate a classifier's performance on a new dataset? We study the case where data is plentiful, but labels are expensive. We show that by making a few reasonable assumptions on the structure of the data, it is possible to estimate performance curves, with confidence bounds, using a small number of ground truth labels. Our approach, which we call Semisupervised Performance Evaluation (SPE), is based on a generative model for the classifier's confidence scores. In addition to estimating the performance of classifiers on new datasets, SPE can be used to re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.2162","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":""},"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":"1210.2162","created_at":"2026-05-18T03:43:50.922741+00:00"},{"alias_kind":"arxiv_version","alias_value":"1210.2162v1","created_at":"2026-05-18T03:43:50.922741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.2162","created_at":"2026-05-18T03:43:50.922741+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBY2SO75IZM4","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBY2SO75IZM4IVY2","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBY2SO75","created_at":"2026-05-18T12:27:25.539911+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/WBY2SO75IZM4IVY2ZBOTRKJUS7","json":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7.json","graph_json":"https://pith.science/api/pith-number/WBY2SO75IZM4IVY2ZBOTRKJUS7/graph.json","events_json":"https://pith.science/api/pith-number/WBY2SO75IZM4IVY2ZBOTRKJUS7/events.json","paper":"https://pith.science/paper/WBY2SO75"},"agent_actions":{"view_html":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7","download_json":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7.json","view_paper":"https://pith.science/paper/WBY2SO75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1210.2162&json=true","fetch_graph":"https://pith.science/api/pith-number/WBY2SO75IZM4IVY2ZBOTRKJUS7/graph.json","fetch_events":"https://pith.science/api/pith-number/WBY2SO75IZM4IVY2ZBOTRKJUS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7/action/storage_attestation","attest_author":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7/action/author_attestation","sign_citation":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7/action/citation_signature","submit_replication":"https://pith.science/pith/WBY2SO75IZM4IVY2ZBOTRKJUS7/action/replication_record"}},"created_at":"2026-05-18T03:43:50.922741+00:00","updated_at":"2026-05-18T03:43:50.922741+00:00"}