{"id":"W2087859840","doi":"10.1007/s10844-009-0096-5","title":"Evaluating information retrieval system performance based on user preference","year":2009,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Information retrieval; Preference; Rank (graph theory); Precision and recall; Measure (data warehouse); Relevance feedback; Document retrieval; Data mining; Artificial intelligence; Image retrieval; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003330251,0.0002335824,0.0003507728,0.001021365,0.0002349686,0.001060002,0.001025725,0.0001400995,0.00001165247],"category_scores_gemma":[0.000324921,0.0001759787,0.0001639579,0.000845939,0.00002021695,0.01362536,0.00004545123,0.000442225,0.0005271869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005164701,"about_ca_system_score_gemma":0.0004112405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003750504,"about_ca_topic_score_gemma":3.027093e-8,"domain_scores_codex":[0.9947683,0.0001504261,0.002383783,0.00008453657,0.002273022,0.0003399839],"domain_scores_gemma":[0.994579,0.0001293947,0.002074435,0.0004470187,0.002557389,0.0002128037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001431538,0.0002014275,0.0006872615,0.001172991,0.00006410896,0.000008470997,0.009247165,0.5522454,0.0002440872,0.08408574,0.003191887,0.3474199],"study_design_scores_gemma":[0.0008642125,0.002209312,0.002117003,0.0007444338,0.00001372832,0.0001683873,0.0008880615,0.972643,0.004445682,0.000009154788,0.01563407,0.0002629306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1092518,0.00002926483,0.87791,0.0002909479,0.002256649,0.0007900308,0.00001070108,0.0001650333,0.009295506],"genre_scores_gemma":[0.9951518,0.00001758853,0.004027694,0.000623383,0.0001039476,0.000005011333,0.00001647634,0.000003383907,0.00005070103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8859,"threshold_uncertainty_score":0.999977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07183585331902738,"score_gpt":0.3096554805127487,"score_spread":0.2378196271937213,"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."}}