{"id":"W2795483004","doi":"10.1007/978-3-319-89656-4_32","title":"Towards a Comprehensive Evaluation of Recommenders: A Cognition-Based Approach","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"RSS; Computer science; Recommender system; Taxonomy (biology); Metric (unit); Cognition; Artificial intelligence; Machine learning; World Wide Web","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":[0.03230786,0.001909951,0.002769403,0.00766524,0.001548594,0.01285564,0.00339362,0.003609738,0.006429092],"category_scores_gemma":[0.1001882,0.0006619403,0.001514212,0.006632672,0.002659974,0.01228987,0.004026154,0.002684579,0.001650794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002902933,"about_ca_system_score_gemma":0.003021372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004166557,"about_ca_topic_score_gemma":0.005548289,"domain_scores_codex":[0.9567126,0.019349,0.002479693,0.002390413,0.01823638,0.0008320767],"domain_scores_gemma":[0.9071723,0.05519149,0.00431044,0.008216991,0.02259172,0.002517072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007509214,0.0008946357,0.03371128,0.002918012,0.001427464,0.0001547821,0.002124023,0.02249334,0.005167052,0.1804847,0.01431899,0.7355548],"study_design_scores_gemma":[0.0002633445,0.00320785,0.05231274,0.0029972,0.001804761,0.000930071,0.005723204,0.3706413,0.01195441,0.4798303,0.06983782,0.0004969545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08987591,0.0184674,0.8203003,0.005009125,0.0003072896,0.0008417952,0.001142429,0.001236327,0.06281937],"genre_scores_gemma":[0.5280616,0.003422176,0.4605589,0.0005529449,0.0003025926,0.000496969,0.001495678,0.0001922352,0.004916902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03230786,"threshold_uncertainty_score":0.1708624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07912975177512617,"score_gpt":0.306175133184565,"score_spread":0.2270453814094389,"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."}}