{"id":"W2005955505","doi":"10.1198/106186005x47291","title":"Distance Measures and Smoothing Methodology for Imputing Features of Documents","year":2005,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Smoothing; Computer science; Class (philosophy); Missing data; Distance measures; Data mining; Artificial intelligence; Machine learning","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":[0.01643595,0.001467501,0.002094876,0.009412296,0.001627591,0.003095038,0.004420523,0.002987321,0.002278192],"category_scores_gemma":[0.08010422,0.000892451,0.00263525,0.009738325,0.003049362,0.006292149,0.003112473,0.004444443,0.00157827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00175281,"about_ca_system_score_gemma":0.00212735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002139995,"about_ca_topic_score_gemma":0.001709123,"domain_scores_codex":[0.9878786,0.005204823,0.001019894,0.00224857,0.003325841,0.0003222841],"domain_scores_gemma":[0.948255,0.03026902,0.003794307,0.01124252,0.005713434,0.0007257571],"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":[0.0002059244,0.0001354841,0.00471366,0.0004956538,0.0004930249,0.0002205745,0.0006744484,0.09765903,0.00469844,0.3565312,0.005400122,0.5287724],"study_design_scores_gemma":[0.00005820709,0.0002163545,0.002830699,0.0001000768,0.0001332249,0.0004933933,0.0001226137,0.4757973,0.005662004,0.4959875,0.0184025,0.0001960631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001598782,0.0002965492,0.997479,0.0001299079,0.00004915959,0.00002460528,0.00006069675,0.000164847,0.0001964528],"genre_scores_gemma":[0.05863409,0.0008532502,0.9367713,0.0001758018,0.0004456804,0.000369067,0.0005991388,0.0002622641,0.001889476],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01643595,"threshold_uncertainty_score":0.08692265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03319004123874491,"score_gpt":0.3298004024824565,"score_spread":0.2966103612437116,"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."}}