{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XYJ3YEDSAZOHDNTQL3KKUSRTX4","short_pith_number":"pith:XYJ3YEDS","schema_version":"1.0","canonical_sha256":"be13bc1072065c71b6705ed4aa4a33bf12a0efa8ca6916cc8d9cff1cd21ed39b","source":{"kind":"arxiv","id":"1808.10585","version":4},"attestation_state":"computed","paper":{"title":"On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Krishna Menon, Gang Niu, Masashi Sugiyama, Nan Lu","submitted_at":"2018-08-31T03:18:00Z","abstract_excerpt":"Empirical risk minimization (ERM), with proper loss function and regularization, is the common practice of supervised classification. In this paper, we study training arbitrary (from linear to deep) binary classifier from only unlabeled (U) data by ERM. We prove that it is impossible to estimate the risk of an arbitrary binary classifier in an unbiased manner given a single set of U data, but it becomes possible given two sets of U data with different class priors. These two facts answer a fundamental question---what the minimal supervision is for training any binary classifier from only U dat"},"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":"1808.10585","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-31T03:18:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c43b2ff1c7f86ea06c106550553c14501192c028c52389aea1702a0baebf8ecd","abstract_canon_sha256":"9f5334437839c4d22c171f95a98f1dddb1d0fde69d72ebe44467d0d2c1920d57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:33.351338Z","signature_b64":"mqU3F8x3VYH4W98VqDaRKou5RO0IiCxr6orOSqyqDsfZLj1yl5ZiHiylFJFT8UX0OQNmt+azte9g1avNmljqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be13bc1072065c71b6705ed4aa4a33bf12a0efa8ca6916cc8d9cff1cd21ed39b","last_reissued_at":"2026-05-17T23:51:33.350703Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:33.350703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Krishna Menon, Gang Niu, Masashi Sugiyama, Nan Lu","submitted_at":"2018-08-31T03:18:00Z","abstract_excerpt":"Empirical risk minimization (ERM), with proper loss function and regularization, is the common practice of supervised classification. In this paper, we study training arbitrary (from linear to deep) binary classifier from only unlabeled (U) data by ERM. We prove that it is impossible to estimate the risk of an arbitrary binary classifier in an unbiased manner given a single set of U data, but it becomes possible given two sets of U data with different class priors. These two facts answer a fundamental question---what the minimal supervision is for training any binary classifier from only U dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10585","kind":"arxiv","version":4},"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":"1808.10585","created_at":"2026-05-17T23:51:33.350796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10585v4","created_at":"2026-05-17T23:51:33.350796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10585","created_at":"2026-05-17T23:51:33.350796+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYJ3YEDSAZOH","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYJ3YEDSAZOHDNTQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYJ3YEDS","created_at":"2026-05-18T12:33:04.347982+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/XYJ3YEDSAZOHDNTQL3KKUSRTX4","json":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4.json","graph_json":"https://pith.science/api/pith-number/XYJ3YEDSAZOHDNTQL3KKUSRTX4/graph.json","events_json":"https://pith.science/api/pith-number/XYJ3YEDSAZOHDNTQL3KKUSRTX4/events.json","paper":"https://pith.science/paper/XYJ3YEDS"},"agent_actions":{"view_html":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4","download_json":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4.json","view_paper":"https://pith.science/paper/XYJ3YEDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10585&json=true","fetch_graph":"https://pith.science/api/pith-number/XYJ3YEDSAZOHDNTQL3KKUSRTX4/graph.json","fetch_events":"https://pith.science/api/pith-number/XYJ3YEDSAZOHDNTQL3KKUSRTX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4/action/storage_attestation","attest_author":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4/action/author_attestation","sign_citation":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4/action/citation_signature","submit_replication":"https://pith.science/pith/XYJ3YEDSAZOHDNTQL3KKUSRTX4/action/replication_record"}},"created_at":"2026-05-17T23:51:33.350796+00:00","updated_at":"2026-05-17T23:51:33.350796+00:00"}