{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02011039,0.002272442,0.002146044,0.008261758,0.001467151,0.006423756,0.002956758,0.001496112,0.03592943],"category_scores_gemma":[0.1023196,0.001703523,0.003636073,0.007855064,0.001520673,0.005520931,0.005403624,0.004251647,0.009262721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007682633,"about_ca_system_score_gemma":0.003486587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002800533,"about_ca_topic_score_gemma":0.004022658,"domain_scores_codex":[0.9888802,0.006280566,0.001400142,0.0016289,0.001477893,0.0003323617],"domain_scores_gemma":[0.9015681,0.08408156,0.003733317,0.006748907,0.003168841,0.0006993067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001109139,0.0002637641,0.01954437,0.007066017,0.001915894,0.001232698,0.007862434,0.01172336,0.008104412,0.1124224,0.3282968,0.5004588],"study_design_scores_gemma":[0.0005056554,0.0003558394,0.008892591,0.002208633,0.0008037688,0.001787714,0.001476001,0.09568246,0.01326249,0.3512774,0.5232012,0.0005461055],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006985484,0.0008340012,0.8990484,0.001230025,0.000468542,0.0005190176,0.0335445,0.05325894,0.004111094],"genre_scores_gemma":[0.03213029,0.0004600974,0.9334677,0.0004389897,0.0001397212,0.002593601,0.0148768,0.01455822,0.001334498],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03592943,"threshold_uncertainty_score":0.1201959,"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."}}