{"id":"W3094281686","doi":"10.18637/jss.v114.i04","title":"Exploring Data Subsets with <b>vtree</b>","year":2025,"lang":"en","type":"preprint","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agricultural Research Institute of Ontario","funders":"","keywords":"Venn diagram; Contingency table; Variable (mathematics); Computer science; Missing data; Data mining; Diagram; Tree (set theory); Algorithm; Theoretical computer science; Mathematics; Machine learning; Combinatorics; Database","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008792033,0.0003452149,0.0008649179,0.0003679731,0.00009353971,0.000524183,0.006344751,0.0001170331,0.00005502463],"category_scores_gemma":[0.001619478,0.0002542805,0.0001013202,0.0004499664,0.0001026462,0.001780273,0.005508028,0.001368133,0.00002325198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389464,"about_ca_system_score_gemma":0.0009907254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006468037,"about_ca_topic_score_gemma":0.00004587571,"domain_scores_codex":[0.9965489,0.0001651957,0.0009543177,0.0007221288,0.00122853,0.0003809516],"domain_scores_gemma":[0.9946007,0.001076656,0.000835727,0.002565966,0.000593018,0.000328005],"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":[0.0003325866,0.0008459655,0.01735084,0.001844501,0.003045183,0.008691052,0.0009148361,0.006362213,0.000006213253,0.06093398,0.1185628,0.7811099],"study_design_scores_gemma":[0.01079188,0.003448606,0.2225675,0.02534421,0.009797005,0.003322678,0.0006478024,0.2692293,0.0004518871,0.2091658,0.2353337,0.009899644],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004185463,0.0003136668,0.9957938,0.0006585303,0.0007955568,0.0001015197,0.001732203,0.00007406436,0.0001121803],"genre_scores_gemma":[0.01146113,0.0003498798,0.9873245,0.0001938008,0.0002563384,0.000007399521,0.0003038512,0.00001854007,0.00008453865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7712103,"threshold_uncertainty_score":0.9999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1660587710562463,"score_gpt":0.3275761359707859,"score_spread":0.1615173649145396,"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."}}