{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007540761,0.0006228835,0.0005585395,0.003911998,0.0007753895,0.002036896,0.0004923398,0.0005354408,0.01033906],"category_scores_gemma":[0.004640571,0.0002385249,0.0006235469,0.003450992,0.0005242472,0.001127999,0.001322478,0.0008254062,0.001358483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004196283,"about_ca_system_score_gemma":0.0006720197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004155216,"about_ca_topic_score_gemma":0.004951001,"domain_scores_codex":[0.9994202,0.0001866521,0.00004509613,0.0000963858,0.0001994901,0.00005216317],"domain_scores_gemma":[0.9960797,0.002654833,0.0002328263,0.000387066,0.0005008703,0.000144681],"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":[0.001630629,0.0003433988,0.02947787,0.002804879,0.0004464108,0.004961999,0.01106679,0.04934147,0.06009337,0.09795258,0.1110293,0.6308514],"study_design_scores_gemma":[0.0001831974,0.0002697047,0.03963736,0.0006847593,0.0002010236,0.003969116,0.006448237,0.4523052,0.04983807,0.1795352,0.2666273,0.0003008139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2007783,0.003315848,0.7315771,0.002666458,0.0003371434,0.0003340922,0.02518411,0.02034299,0.01546397],"genre_scores_gemma":[0.4632649,0.001214636,0.5186352,0.0002556685,0.0001294265,0.000301925,0.01023376,0.002280232,0.003684242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01033906,"threshold_uncertainty_score":0.03458756,"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."}}