{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UP7W2OVZEGVZCABBCHWU7SGKRY","short_pith_number":"pith:UP7W2OVZ","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"},"canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","source":{"kind":"arxiv","id":"1806.06123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06123","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06123v1","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06123","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"UP7W2OVZEGVZ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UP7W2OVZEGVZCABB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UP7W2OVZ","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UP7W2OVZEGVZCABBCHWU7SGKRY","target":"record","payload":{"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"},"canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","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"},"source_kind":"arxiv","source_id":"1806.06123","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GA1eUEIeEkUZ49u/RSAyrS7rBxPbl/UQgoWlg7Ljc1MMShn+5zaHuGxO3dUVD0AhBCoVwBNCtCV5gjjpZ7oqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T22:17:37.477716Z"},"content_sha256":"80017bf9073880abd3946a2d69adf56857518225e0c3ea17e7116253a58b3015","schema_version":"1.0","event_id":"sha256:80017bf9073880abd3946a2d69adf56857518225e0c3ea17e7116253a58b3015"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UP7W2OVZEGVZCABBCHWU7SGKRY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4m7YzTwWSMXbbtY1XradG+0du+bxZWlGq0cg2IFbd7rOCAr1PDudSAKsOJ4kVQUyNCOEPNBTr1+/gEB1ZuJMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T22:17:37.478053Z"},"content_sha256":"0dda8bc25ed5c76c6f5e97987a3736008981b05b195aced26b64dad5d7c772a8","schema_version":"1.0","event_id":"sha256:0dda8bc25ed5c76c6f5e97987a3736008981b05b195aced26b64dad5d7c772a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/bundle.json","state_url":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T22:17:37Z","links":{"resolver":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY","bundle":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/bundle.json","state":"https://pith.science/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UP7W2OVZEGVZCABBCHWU7SGKRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UP7W2OVZEGVZCABBCHWU7SGKRY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d5465424d1ac76ae017198d652401cfbb9ac46361c38b061ef8adc75e432fb0b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T20:47:50Z","title_canon_sha256":"4034969e3752796f5495ac2329bacbda5cca5e5f0ee45896599d9c18ee2bdf77"},"schema_version":"1.0","source":{"id":"1806.06123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06123","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06123v1","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06123","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"UP7W2OVZEGVZ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UP7W2OVZEGVZCABB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UP7W2OVZ","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:0dda8bc25ed5c76c6f5e97987a3736008981b05b195aced26b64dad5d7c772a8","target":"graph","created_at":"2026-05-18T00:13:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Percy Liang, Stephen Mussmann","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T20:47:50Z","title":"On the Relationship between Data Efficiency and Error for Uncertainty Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06123","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80017bf9073880abd3946a2d69adf56857518225e0c3ea17e7116253a58b3015","target":"record","created_at":"2026-05-18T00:13:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d5465424d1ac76ae017198d652401cfbb9ac46361c38b061ef8adc75e432fb0b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-15T20:47:50Z","title_canon_sha256":"4034969e3752796f5495ac2329bacbda5cca5e5f0ee45896599d9c18ee2bdf77"},"schema_version":"1.0","source":{"id":"1806.06123","kind":"arxiv","version":1}},"canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3ff6d3ab921ab91002111ed4fc8ca8e0706865738653f937e7ddf708fdfd7f2","first_computed_at":"2026-05-18T00:13:03.587345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:03.587345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+g2q38YQA/pks074TGzHkorvsGQYJ+7FSV4A2FTYWt/0pB6p0kPr1Wj9ZTDUfk/AXiitxlOAtPxf5GQvBvvuAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:03.587874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80017bf9073880abd3946a2d69adf56857518225e0c3ea17e7116253a58b3015","sha256:0dda8bc25ed5c76c6f5e97987a3736008981b05b195aced26b64dad5d7c772a8"],"state_sha256":"9e4736c95d7079deffd85f3ab504253af3345397295e2e0b54fef48fd6ed64a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0xs/fX9Ox5Vrqq1tL70BeEsIUYTlbI5AuE4HTz4lOQz+NwMzd4upafPgIMAeuNokbR67tjG8nVgZFhNfL0Z/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T22:17:37.479879Z","bundle_sha256":"e1904b59a7d7ac901c343c27f80f652f69db85cbb20ceb72767a883554a86dda"}}