{"id":"W4385681511","doi":"10.48550/arxiv.2308.03079","title":"Visualization of Extremely Sparse Contingency Table by Taxicab Correspondence Analysis: A Case Study of Textual Data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Visualization; Contingency table; Correspondence analysis; Dimensionality reduction; Computer science; Dimension (graph theory); Set (abstract data type); Data set; Table (database); Data mining; Information retrieval; Artificial intelligence; Mathematics; Machine learning; Combinatorics","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":[0.0008632555,0.0002219147,0.0007234748,0.0001103923,0.0001276261,0.00003139978,0.0009037979,0.0001770625,0.0003711394],"category_scores_gemma":[0.0004697238,0.0001224212,0.0001665248,0.002709746,0.0001208977,0.0001117175,0.0009657961,0.0001906369,0.000005540453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000214698,"about_ca_system_score_gemma":0.00002225773,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01659286,"about_ca_topic_score_gemma":0.008653739,"domain_scores_codex":[0.9973843,0.0007344473,0.0004986073,0.000993704,0.0001732649,0.0002157245],"domain_scores_gemma":[0.9977048,0.0007402827,0.000666465,0.0004850584,0.0002924969,0.0001108946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001588112,0.01100978,0.7163289,0.0004109406,0.01200445,0.01023832,0.002342656,0.1580851,0.04358711,0.01020731,0.004364573,0.0298328],"study_design_scores_gemma":[0.0008531786,0.001272747,0.07594635,0.0001231449,0.01058457,0.00001601011,0.03737667,0.8701452,0.0004879113,0.001784355,0.0002855104,0.001124359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9791087,0.00005279296,0.01909436,0.000006541484,0.00006409792,0.0002793651,0.001277865,0.0000398919,0.0000763783],"genre_scores_gemma":[0.9980509,0.0000732589,0.0001321137,0.000006188267,0.00002626896,7.648099e-7,0.0005686663,0.000001905309,0.001139922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7120602,"threshold_uncertainty_score":0.9899557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3319689067478558,"score_gpt":0.2929399133416865,"score_spread":0.03902899340616928,"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."}}