{"id":"W2612181456","doi":"10.1007/978-1-4899-7502-7_35-1","title":"Categorical Data Clustering","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Domain (mathematical analysis); Cluster (spacecraft); Artificial intelligence; Machine learning; Mathematics","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":[0.001183179,0.0004523384,0.0006367969,0.0002899636,0.0002251939,0.0001301371,0.005330308,0.0002498208,0.00008041726],"category_scores_gemma":[0.0008277334,0.0003854818,0.00003961577,0.00008089704,0.0001742149,0.001129833,0.02104529,0.00102479,0.00004852023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004091473,"about_ca_system_score_gemma":0.0001649128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004656219,"about_ca_topic_score_gemma":0.00002991753,"domain_scores_codex":[0.9963561,0.00008965081,0.0006106719,0.001738038,0.0007007042,0.0005048683],"domain_scores_gemma":[0.9946405,0.0008686422,0.0004335289,0.003743585,0.0000818816,0.00023183],"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":[0.00001688293,0.00001124667,0.0001718911,0.0001544722,0.00007598356,0.0001447196,0.0002293562,0.00003952453,0.000009831557,0.003898571,0.001101596,0.9941459],"study_design_scores_gemma":[0.0003937536,0.0001274178,0.00002282798,0.0003336626,0.00003079089,0.0001307823,0.00001236583,0.2586284,0.000001122839,0.0009581239,0.7388423,0.000518473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000009620826,0.004308857,0.61049,0.0004601516,0.0004762417,0.0001823369,0.0004557639,0.0002524805,0.3833646],"genre_scores_gemma":[0.001208055,0.01731175,0.3654005,0.00005666138,0.001199323,0.000007455319,0.002012447,0.0002180583,0.6125858],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9936274,"threshold_uncertainty_score":0.9998597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05026195322463737,"score_gpt":0.3275556204352275,"score_spread":0.2772936672105901,"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."}}