{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08425798,0.002126413,0.002361311,0.00523719,0.001769069,0.008444688,0.003520615,0.005283872,0.00305907],"category_scores_gemma":[0.3382526,0.0005856094,0.001825787,0.005545661,0.002683932,0.01644929,0.002903613,0.004253185,0.0006134143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004101512,"about_ca_system_score_gemma":0.001693389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002603725,"about_ca_topic_score_gemma":0.001821567,"domain_scores_codex":[0.8932891,0.08107236,0.006029473,0.005866819,0.0121558,0.001586513],"domain_scores_gemma":[0.5815399,0.3591687,0.013224,0.02237002,0.02150484,0.002192584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00138828,0.002102409,0.01826566,0.002571127,0.001018516,0.0002000392,0.0020881,0.2498516,0.005526138,0.4240253,0.008165528,0.2847972],"study_design_scores_gemma":[0.0002656105,0.001845199,0.005752254,0.0005835943,0.0002284174,0.0002902341,0.0006798196,0.7238417,0.002925788,0.2559385,0.007420865,0.0002280236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05383091,0.003202115,0.9319788,0.002158104,0.0003404978,0.0005321135,0.0003973616,0.00039833,0.007161778],"genre_scores_gemma":[0.4822855,0.0009948385,0.5128312,0.0005605498,0.0003738141,0.0009271036,0.001053617,0.0001740234,0.0007993711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08425798,"threshold_uncertainty_score":0.4456041,"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."}}