{"id":"W2954147681","doi":"10.1145/3331184.3331355","title":"Unbiased Low-Variance Estimators for Precision and Related Information Retrieval Effectiveness Measures","year":2019,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Pooling; Variance (accounting); Bias of an estimator; Computer science; Minimum-variance unbiased estimator; Relevance (law); Statistics; Rank (graph theory); Sampling (signal processing); Mathematics; Artificial intelligence; Detector","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001096803,0.0001104585,0.0001474239,0.0001415224,0.0001167555,0.000264629,0.0002796384,0.0001067308,0.00002321163],"category_scores_gemma":[0.0003080732,0.0000870166,0.00004724953,0.000400849,0.00002409594,0.003047843,0.00009692147,0.0001051911,0.0001729047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004771677,"about_ca_system_score_gemma":0.00008307739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000672134,"about_ca_topic_score_gemma":2.296415e-7,"domain_scores_codex":[0.9988965,0.00006161373,0.0002968423,0.0001597032,0.000382559,0.0002027951],"domain_scores_gemma":[0.9988942,0.0003303538,0.00009896384,0.0002677358,0.0003229876,0.00008580932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002373541,0.0002307542,0.01429101,0.00143581,0.0001119114,0.000005321657,0.005573901,0.004046912,0.02030898,0.4344478,0.001247562,0.5159265],"study_design_scores_gemma":[0.005235346,0.0007929633,0.1541657,0.0002228051,0.00001565707,0.00003549247,0.00007033716,0.7694833,0.05977479,0.005198478,0.004411594,0.000593472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4115883,0.00001043548,0.5853886,0.0001043885,0.0004551057,0.00100871,0.000005064946,0.0001520716,0.00128739],"genre_scores_gemma":[0.9897482,0.000004456706,0.009864955,0.00009979252,0.000006378138,0.00001629912,0.00001648283,0.000004156725,0.000239229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7654364,"threshold_uncertainty_score":0.3548434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009846621620026131,"score_gpt":0.2519131012687099,"score_spread":0.2420664796486837,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}