{"id":"W2083200098","doi":"10.6017/ital.v33i2.5341","title":"The Importance of Identifying and Accommodating E-Resource Usage Data for the Presence of Outliers. The Negative Impacts of Inaccurate E-Journal Usage Data.","year":2014,"lang":"en","type":"article","venue":"Information Technology and Libraries","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Outlier; Upload; Computer science; Identification (biology); Sample (material); Usage data; Resource (disambiguation); Data mining; Statistics; Data science; Information retrieval; World Wide Web; Mathematics; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007572049,0.00007889903,0.0001846965,0.0001586734,0.0006501535,0.0004715378,0.003178232,0.00006055796,0.000005949353],"category_scores_gemma":[0.01591218,0.00003576897,0.00001713855,0.0004664466,0.001441671,0.006341713,0.002779552,0.000178232,6.239275e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002018382,"about_ca_system_score_gemma":0.00004244549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001744055,"about_ca_topic_score_gemma":0.00004627244,"domain_scores_codex":[0.9983828,0.0001420299,0.0008567452,0.00012724,0.0003565211,0.0001346454],"domain_scores_gemma":[0.9906409,0.006110462,0.001521022,0.001584934,0.0001227246,0.00001989786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001586882,0.00001594385,0.01356578,0.000125302,0.0001290166,1.585119e-7,0.008353327,0.00004216035,0.000046314,0.4987581,0.02334334,0.4554619],"study_design_scores_gemma":[0.000926287,0.0001742232,0.0247588,0.0001414242,0.0000879375,0.00001910897,0.147824,0.04225342,0.003788439,0.4320795,0.3477702,0.0001767357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4865385,0.003820396,0.4534441,0.04886531,0.0004641218,0.001982598,0.002498665,0.00008149719,0.002304841],"genre_scores_gemma":[0.9972798,0.0002410401,0.002142112,0.0002411916,0.00001368629,0.000006646554,0.00004093001,0.000002350704,0.00003220146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5107414,"threshold_uncertainty_score":0.9923772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1325676505123607,"score_gpt":0.3760560784491905,"score_spread":0.2434884279368298,"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."}}