{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006880171,0.00007135922,0.0001934726,0.00009845273,0.00008551833,0.00005581469,0.000148973,0.00003941608,7.743675e-7],"category_scores_gemma":[0.0003176929,0.00005531895,0.00003967429,0.0001187066,0.0001129492,0.0001778011,0.00003842063,0.0001142546,3.99759e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009339701,"about_ca_system_score_gemma":0.00003710301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002530934,"about_ca_topic_score_gemma":0.000001239547,"domain_scores_codex":[0.9990848,0.00008070692,0.0003910032,0.0001022747,0.0002494562,0.00009174709],"domain_scores_gemma":[0.9978772,0.001202478,0.000360193,0.00004352574,0.0004505684,0.00006600713],"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":[0.00003691645,0.00003178402,0.0003316287,0.00003581122,0.00003137947,0.000001632986,0.0001891734,0.0001141917,0.0003681272,0.6593113,0.0002807276,0.3392674],"study_design_scores_gemma":[0.0005713487,0.0003013251,0.0432875,0.00004510124,0.0000268541,0.0001278351,0.00002720748,0.02884952,0.001477576,0.9229331,0.00224021,0.0001123926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001894661,0.0007825027,0.9956866,0.001483805,0.00005179042,0.00005595845,0.00001627747,0.00000830065,0.00002014224],"genre_scores_gemma":[0.4232526,0.00008093037,0.5765318,0.00008984684,0.00003397534,6.067899e-7,0.000001108689,0.000001940963,0.000007249869],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4213579,"threshold_uncertainty_score":0.2255841,"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."}}