{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03898222,0.001961212,0.002358616,0.008528313,0.001100511,0.003979619,0.002476768,0.002593937,0.002141516],"category_scores_gemma":[0.3017113,0.0009257839,0.001459092,0.003689488,0.004303393,0.007585249,0.003396939,0.003710065,0.001130967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0024132,"about_ca_system_score_gemma":0.001561697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185831,"about_ca_topic_score_gemma":0.001192486,"domain_scores_codex":[0.9604378,0.01924044,0.001963781,0.00517849,0.01217575,0.001003669],"domain_scores_gemma":[0.7185468,0.2321476,0.01134567,0.02333167,0.01379036,0.0008379022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005077063,0.00031273,0.02194102,0.001186854,0.0009232252,0.0001895744,0.0006555694,0.2542503,0.01010435,0.3578102,0.006397028,0.3457214],"study_design_scores_gemma":[0.00009047447,0.0004537532,0.009775922,0.0004851551,0.0002622653,0.0005962193,0.0001554241,0.6493381,0.01686858,0.3159023,0.005799769,0.0002720442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006284563,0.0009047949,0.9905425,0.0001720531,0.00003984984,0.0001130913,0.0001630447,0.0003365306,0.001443603],"genre_scores_gemma":[0.4215444,0.001444971,0.5709932,0.0005903087,0.0005734012,0.001261919,0.001218706,0.0004336678,0.001939382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03898222,"threshold_uncertainty_score":0.2061601,"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."}}