{"id":"W2111310810","doi":"10.1145/1148170.1148262","title":"Statistical precision of information retrieval evaluation","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Concordance; Population; Information retrieval; Confidence interval; Statistics; Degree (music); Statistical hypothesis testing; Data collection; Test (biology); Artificial intelligence; Mathematics","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":[0.0005499591,0.00004588248,0.00007830852,0.0001247692,0.00002239619,0.00003407607,0.0002225074,0.00002989786,0.00005352787],"category_scores_gemma":[0.0001688422,0.00003862924,0.00002225758,0.0003439371,0.00001846294,0.001219678,0.00006668088,0.00003300899,0.00002299102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004300844,"about_ca_system_score_gemma":0.00003480012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003109322,"about_ca_topic_score_gemma":0.000004411604,"domain_scores_codex":[0.9989877,0.00004138542,0.0002835751,0.00008867666,0.0005252996,0.00007339815],"domain_scores_gemma":[0.999234,0.00008570028,0.0001111082,0.0002574902,0.0002965509,0.0000152017],"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":[0.00000945989,0.00003644426,0.0003623952,0.000005313819,0.000003663206,1.899659e-7,0.00004534424,0.0008726837,0.002431027,0.7295376,0.002575831,0.26412],"study_design_scores_gemma":[0.0002061151,0.00007080677,0.01556617,0.000006322141,0.00001102377,0.00000142465,0.000005284544,0.5960891,0.06921358,0.3175053,0.001233332,0.00009156233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0049689,0.000008971912,0.9836541,0.00005482512,0.00002350613,0.0001228859,0.000001238847,0.0001143119,0.01105121],"genre_scores_gemma":[0.584218,0.000001050291,0.4157148,0.00001509806,0.000005983457,0.000001907628,0.00001349663,8.27482e-7,0.00002885727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5952164,"threshold_uncertainty_score":0.1575255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01181805756965918,"score_gpt":0.3080099634055263,"score_spread":0.2961919058358671,"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."}}