{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02699448,0.0032536,0.002589531,0.01020572,0.0009518289,0.003402697,0.002082035,0.002264658,0.004752423],"category_scores_gemma":[0.08778109,0.0007146577,0.002652098,0.006757345,0.0007590207,0.00379425,0.002074761,0.002518229,0.002019641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002005331,"about_ca_system_score_gemma":0.002136177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003722909,"about_ca_topic_score_gemma":0.004306815,"domain_scores_codex":[0.9630386,0.01776804,0.003752283,0.003265758,0.01165224,0.0005231469],"domain_scores_gemma":[0.9250533,0.04872341,0.004581892,0.006826826,0.01408364,0.0007308911],"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":[0.0007196986,0.000628127,0.009748333,0.003160162,0.001115536,0.0001929539,0.0006299567,0.1021482,0.005259039,0.01927208,0.03429083,0.8228351],"study_design_scores_gemma":[0.0002550532,0.001638423,0.01090295,0.0006422439,0.0004477309,0.0007145431,0.0003645864,0.9265295,0.0071523,0.01861834,0.03239476,0.0003395687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009099819,0.002800564,0.9743795,0.0003336882,0.000190268,0.001050521,0.002126499,0.005054968,0.004964138],"genre_scores_gemma":[0.1068967,0.001004863,0.8837096,0.0001983044,0.0001895134,0.002146335,0.003320828,0.0005518285,0.001982035],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02699448,"threshold_uncertainty_score":0.1427622,"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."}}