{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1517296,0.002222696,0.004257347,0.009435309,0.004118806,0.01283502,0.004737952,0.006168974,0.003401253],"category_scores_gemma":[0.4305668,0.001978989,0.001645238,0.005694316,0.01218211,0.01969589,0.009494485,0.005486071,0.0007946172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008358059,"about_ca_system_score_gemma":0.004304776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002632966,"about_ca_topic_score_gemma":0.001340357,"domain_scores_codex":[0.7619199,0.1573387,0.01401956,0.02521574,0.03882136,0.002684615],"domain_scores_gemma":[0.5184613,0.3986451,0.02932931,0.02144172,0.02894537,0.003177179],"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":[0.0006813184,0.0002081588,0.02717591,0.001359739,0.0007981609,0.0004464717,0.004807076,0.06320614,0.001719681,0.6151987,0.005322352,0.2790763],"study_design_scores_gemma":[0.0002171686,0.000265448,0.004760244,0.0004300561,0.000268768,0.0005529802,0.0005120935,0.1973519,0.002101582,0.7798671,0.01347438,0.0001982745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04278415,0.006982482,0.9258305,0.007486515,0.0004036028,0.000756843,0.00019562,0.0007079719,0.01485234],"genre_scores_gemma":[0.7814409,0.001385486,0.2112347,0.001368045,0.0009421436,0.0008920407,0.0001956064,0.0001639573,0.00237699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1517296,"threshold_uncertainty_score":0.8024325,"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."}}