{"id":"W2119387217","doi":"10.1109/tkde.2008.77","title":"Bias and Controversy in Evaluation Systems","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Set (abstract data type); Object (grammar); Feature (linguistics); Information retrieval; Data set; Data science; Artificial intelligence; Data mining; Machine learning","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":[0.0004260021,0.00009434416,0.0001323295,0.0001753055,0.00006557798,0.00005640066,0.0002076719,0.00004541811,0.00000108276],"category_scores_gemma":[0.000006061748,0.00008996967,0.00001099802,0.0001607436,0.000009806508,0.0005437281,0.000007372378,0.0001029451,0.000003116504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003087398,"about_ca_system_score_gemma":0.00002471251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008641124,"about_ca_topic_score_gemma":0.00003406583,"domain_scores_codex":[0.9993213,0.00003866727,0.0001601247,0.0002703742,0.00009416199,0.0001153045],"domain_scores_gemma":[0.9993792,0.0001036133,0.0000202812,0.0004197874,0.0000276234,0.00004954994],"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":[0.00005252395,0.001143976,0.001918804,0.001244449,0.0003806052,0.0001390549,0.01304843,0.05505646,0.006612669,0.01673604,0.009736879,0.8939301],"study_design_scores_gemma":[0.0004056788,0.00003859074,0.0004602867,0.00007990502,0.00000645289,0.00007472407,0.0000171541,0.9936774,0.0005807853,0.0000101972,0.004527522,0.0001213544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00989875,0.001533589,0.9874365,0.0000351758,0.0004843295,0.0002168658,0.00001372282,0.0001189889,0.0002620989],"genre_scores_gemma":[0.9974378,0.0003758326,0.002068,0.000006524734,0.0000257812,0.00003769187,0.000002992476,0.000006311753,0.00003911849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.987539,"threshold_uncertainty_score":0.3668857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09300923597913141,"score_gpt":0.2950924542262088,"score_spread":0.2020832182470774,"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."}}