{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002537911,0.0005209566,0.0007138634,0.001112534,0.0001682975,0.0002886322,0.002508132,0.0003776147,0.0000655918],"category_scores_gemma":[0.00008683216,0.000473343,0.0001977333,0.0006711665,0.0006524495,0.0004475003,0.0006851769,0.0004951733,0.000009444275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003633888,"about_ca_system_score_gemma":0.001312571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003477154,"about_ca_topic_score_gemma":0.00001687152,"domain_scores_codex":[0.9948977,0.0001801981,0.0007708563,0.001411911,0.002261204,0.0004781382],"domain_scores_gemma":[0.9955435,0.0003429693,0.000645962,0.001499904,0.001838301,0.0001293455],"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":[0.000009999159,0.0001131108,0.00001287796,0.0001703099,0.00003844556,0.000006638143,0.00123043,0.004372995,0.0001038147,0.006269475,0.0002695509,0.9874024],"study_design_scores_gemma":[0.000550809,0.0002798143,0.00003759371,0.0006686276,0.00003353504,0.00002981522,0.000001117658,0.7964404,0.003678622,0.1969213,0.0008259127,0.0005324542],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004235205,0.0003235109,0.9756687,0.0004148639,0.0009799791,0.001030851,0.000009619236,0.0001834568,0.02134673],"genre_scores_gemma":[0.3489326,0.00001577158,0.6496304,0.00100155,0.0002795437,0.00006028846,0.00001892749,0.00003319744,0.00002763948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9868699,"threshold_uncertainty_score":0.9997718,"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."}}