{"id":"W3039910856","doi":"10.5815/ijitcs.2019.12.01","title":"ComPer: A Comprehensive Performance Evaluation Method for Recommender Systems","year":2019,"lang":"en","type":"article","venue":"International Journal of Information Technology and Computer Science","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Recommender system; Metric (unit); Simple (philosophy); Data science; Artificial intelligence; Machine learning; Data mining","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":[0.001945733,0.000112339,0.0002097874,0.001460828,0.000120568,0.0004244486,0.001640422,0.00008416082,0.000003703723],"category_scores_gemma":[0.00003477321,0.00009270663,0.00004984671,0.0005386547,0.00008466945,0.003950002,0.0003296281,0.0001628221,0.000007875833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267104,"about_ca_system_score_gemma":0.0001997547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003614534,"about_ca_topic_score_gemma":1.009336e-7,"domain_scores_codex":[0.9983492,0.00004155323,0.0006186168,0.0001647695,0.0006555306,0.0001702888],"domain_scores_gemma":[0.99611,0.0001044053,0.0006861276,0.0002492439,0.002797961,0.00005221739],"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":[0.00001790678,0.00002447632,0.001218147,0.00002627686,0.00005370034,5.407962e-7,0.0004133265,0.001221762,0.0002641373,0.218744,0.0008766187,0.7771391],"study_design_scores_gemma":[0.0008619112,0.0003903253,0.001594749,0.0001085813,0.000005145516,0.0005739104,0.0001223325,0.9657698,0.002156694,0.004208942,0.02407718,0.0001304244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03820957,0.0001061964,0.9561422,0.001689903,0.003059474,0.0003739893,0.000001872813,0.00006737882,0.0003494429],"genre_scores_gemma":[0.6782045,0.00004339418,0.3212223,0.0004404223,0.00006042331,0.0000188055,0.00000154317,0.000002225008,0.000006354815],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9645481,"threshold_uncertainty_score":0.4092968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789171602624898,"score_gpt":0.307159648440523,"score_spread":0.289267932414274,"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."}}