{"id":"W4253573012","doi":"10.1137/1.9781611976335.ch2","title":"Chapter 2: Data Types","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Data type; Unstructured data; Cluster analysis; Information retrieval; Data mining; Artificial intelligence; Big data; Programming language","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"],"consensus_categories":[],"category_scores_codex":[0.0003462966,0.0003980145,0.000553336,0.00003350584,0.0002317795,0.0002204758,0.001597287,0.0005201459,0.00001514338],"category_scores_gemma":[0.0000312866,0.0003627515,0.0002119403,0.00001920667,0.0001941774,0.00008155675,0.002401154,0.0006982326,0.00003180329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003753271,"about_ca_system_score_gemma":0.0001182306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.093401e-7,"about_ca_topic_score_gemma":4.927336e-7,"domain_scores_codex":[0.9979653,0.000002055961,0.0004161365,0.00083674,0.0004434213,0.0003363712],"domain_scores_gemma":[0.9980916,0.000259457,0.0002558793,0.001137492,0.00006240655,0.000193162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007845862,0.000006670226,5.413559e-9,0.0001654562,0.0001739752,0.000001605931,0.0004587747,0.000002033652,0.00008418173,0.8852327,0.003089882,0.1107768],"study_design_scores_gemma":[0.001165202,0.0001122149,1.043874e-8,0.0001803718,0.0001114405,0.00001155406,0.00007077576,0.02218186,0.0003529858,0.5585996,0.41653,0.0006839858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.00000346574,0.000170163,0.4578216,0.0007709811,0.0003357431,0.002116112,0.0004808352,0.000365035,0.537936],"genre_scores_gemma":[0.0001683396,0.00009930709,0.7592717,0.0004797523,0.001973368,0.0001244773,0.0001625704,0.0002044492,0.2375161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4134401,"threshold_uncertainty_score":0.9998825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1804361474924072,"score_gpt":0.302795166268206,"score_spread":0.1223590187757988,"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."}}