{"id":"W4224313808","doi":"10.1145/3485447.3512106","title":"MCL: Mixed-Centric Loss for Collaborative Filtering","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM Web Conference 2022","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Pairwise comparison; Weighting; Collaborative filtering; Representation (politics); Information loss; Process (computing); Code (set theory); Machine learning; Graph; Preference; Data mining; Artificial intelligence; Theoretical computer science; Recommender system; Statistics; Mathematics","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":[0.008119684,0.001964919,0.002285369,0.001503348,0.0009832231,0.002166408,0.004429154,0.003868733,0.004408055],"category_scores_gemma":[0.01810089,0.0006627537,0.001371973,0.002145136,0.00162528,0.004791311,0.003144547,0.003741963,0.002708856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002570274,"about_ca_system_score_gemma":0.001925097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005031495,"about_ca_topic_score_gemma":0.006638641,"domain_scores_codex":[0.995483,0.0019428,0.0002230408,0.0007517747,0.001263338,0.0003360262],"domain_scores_gemma":[0.9927649,0.004085504,0.0004883764,0.001529463,0.0008726429,0.0002590427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000663321,0.0004607762,0.002759591,0.0003089501,0.0002466775,0.0001787684,0.0001834216,0.561621,0.003552386,0.05452221,0.02527336,0.3502295],"study_design_scores_gemma":[0.00002378553,0.00006353504,0.0001557811,0.00001908354,0.00001372666,0.00005123826,0.000008974933,0.9794073,0.000695875,0.01789046,0.001656207,0.00001396681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005387239,0.0004784099,0.9906784,0.000510109,0.00005542604,0.00006039779,0.0002316424,0.001424235,0.001174093],"genre_scores_gemma":[0.4432811,0.0008523106,0.5382318,0.001558982,0.0004137074,0.000611575,0.002055853,0.0006412146,0.01235345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008119684,"threshold_uncertainty_score":0.04294151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03186525361109577,"score_gpt":0.2522746499838609,"score_spread":0.2204093963727651,"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."}}