{"id":"W125764232","doi":"","title":"Exploring more realistic evaluation measures for collaborative filtering","year":2004,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Collaborative filtering; Computer science; Quality (philosophy); Simple (philosophy); Empirical research; Recommender system; Data mining; Artificial intelligence; Information retrieval; Machine learning; Mathematics; Epistemology; Statistics","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":[0.00110971,0.0001565546,0.0001649006,0.0001954546,0.0002315771,0.0002987216,0.0005010564,0.00005430425,0.00001486209],"category_scores_gemma":[0.0006027396,0.0001516285,0.00005382713,0.0004097227,0.00004593863,0.0006772749,0.00005316991,0.0001103592,0.00002786922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002992136,"about_ca_system_score_gemma":0.0005093128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006561182,"about_ca_topic_score_gemma":0.00008873727,"domain_scores_codex":[0.9980232,0.00007389516,0.0003876654,0.0004276109,0.0008765535,0.0002110683],"domain_scores_gemma":[0.9973768,0.0001768833,0.000146388,0.000229896,0.002002695,0.00006736235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001356693,0.00004438739,0.000001058683,0.000006593938,0.000008828762,7.112062e-7,0.0008447774,0.004488743,0.001533996,0.8574138,0.00005394395,0.1355896],"study_design_scores_gemma":[0.00006664205,0.0002076407,0.000106553,0.0001292252,0.000005681357,0.000003260049,0.00047165,0.1161746,0.1473501,0.7345959,0.0006295951,0.0002591371],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001452084,0.00002212625,0.9884026,0.003513216,0.0004723563,0.0006894202,0.00002225214,0.000163479,0.005262442],"genre_scores_gemma":[0.9657739,0.00002374193,0.03306332,0.0001891657,0.0001369183,0.0007758665,0.00001465528,0.000008610902,0.00001378985],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9643219,"threshold_uncertainty_score":0.6183231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5878091667199781,"score_gpt":0.4241198399079391,"score_spread":0.163689326812039,"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."}}