{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UP7W2OVZEGVZCABBCHWU7SGKRY","short_pith_number":"pith:UP7W2OVZ","schema_version":"1.0","canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","source":{"kind":"arxiv","id":"1806.06123","version":1},"attestation_state":"computed","paper":{"title":"On the Relationship between Data Efficiency and Error for Uncertainty Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Percy Liang, Stephen Mussmann","submitted_at":"2018-06-15T20:47:50Z","abstract_excerpt":"While active learning offers potential cost savings, the actual data efficiency---the reduction in amount of labeled data needed to obtain the same error rate---observed in practice is mixed. This paper poses a basic question: when is active learning actually helpful? We provide an answer for logistic regression with the popular active learning algorithm, uncertainty sampling. Empirically, on 21 datasets from OpenML, we find a strong inverse correlation between data efficiency and the error rate of the final classifier. Theoretically, we show that for a variant of uncertainty sampling, the asy"},"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":"1806.06123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T20:47:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4034969e3752796f5495ac2329bacbda5cca5e5f0ee45896599d9c18ee2bdf77","abstract_canon_sha256":"d5465424d1ac76ae017198d652401cfbb9ac46361c38b061ef8adc75e432fb0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:03.587874Z","signature_b64":"+g2q38YQA/pks074TGzHkorvsGQYJ+7FSV4A2FTYWt/0pB6p0kPr1Wj9ZTDUfk/AXiitxlOAtPxf5GQvBvvuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","last_reissued_at":"2026-05-18T00:13:03.587345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:03.587345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Relationship between Data Efficiency and Error for Uncertainty Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Percy Liang, Stephen Mussmann","submitted_at":"2018-06-15T20:47:50Z","abstract_excerpt":"While active learning offers potential cost savings, the actual data efficiency---the reduction in amount of labeled data needed to obtain the same error rate---observed in practice is mixed. This paper poses a basic question: when is active learning actually helpful? We provide an answer for logistic regression with the popular active learning algorithm, uncertainty sampling. Empirically, on 21 datasets from OpenML, we find a strong inverse correlation between data efficiency and the error rate of the final classifier. Theoretically, we show that for a variant of uncertainty sampling, the asy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06123","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":"1806.06123","created_at":"2026-05-18T00:13:03.587432+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06123v1","created_at":"2026-05-18T00:13:03.587432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06123","created_at":"2026-05-18T00:13:03.587432+00:00"},{"alias_kind":"pith_short_12","alias_value":"UP7W2OVZEGVZ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UP7W2OVZEGVZCABB","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UP7W2OVZ","created_at":"2026-05-18T12:32:56.356000+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/UP7W2OVZEGVZCABBCHWU7SGKRY","json":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY.json","graph_json":"https://pith.science/api/pith-number/UP7W2OVZEGVZCABBCHWU7SGKRY/graph.json","events_json":"https://pith.science/api/pith-number/UP7W2OVZEGVZCABBCHWU7SGKRY/events.json","paper":"https://pith.science/paper/UP7W2OVZ"},"agent_actions":{"view_html":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY","download_json":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY.json","view_paper":"https://pith.science/paper/UP7W2OVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06123&json=true","fetch_graph":"https://pith.science/api/pith-number/UP7W2OVZEGVZCABBCHWU7SGKRY/graph.json","fetch_events":"https://pith.science/api/pith-number/UP7W2OVZEGVZCABBCHWU7SGKRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/action/storage_attestation","attest_author":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/action/author_attestation","sign_citation":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/action/citation_signature","submit_replication":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/action/replication_record"}},"created_at":"2026-05-18T00:13:03.587432+00:00","updated_at":"2026-05-18T00:13:03.587432+00:00"}