{"id":"W1963762678","doi":"10.1177/0049124106292362","title":"Addressing Data Sparseness in Contextual Population Research","year":2007,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Variance (accounting); Cluster analysis; Cluster (spacecraft); Monte Carlo method; Statistics; Population; Econometrics; Data mining; 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":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1515619,0.0001385475,0.0003966837,0.0005101249,0.002651283,0.0001824387,0.001268825,0.0005126508,0.0003531359],"category_scores_gemma":[0.03662892,0.0001119714,0.00005884547,0.002078643,0.002684467,0.0003693259,0.0009742483,0.001881405,0.00007413095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004896527,"about_ca_system_score_gemma":0.0002915864,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01025654,"about_ca_topic_score_gemma":0.005521878,"domain_scores_codex":[0.9724012,0.02239275,0.0005701516,0.0008522947,0.002047686,0.00173593],"domain_scores_gemma":[0.9707649,0.02735296,0.00007591872,0.0006185758,0.0009194417,0.0002682219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002621447,0.0003161606,0.2704705,0.0000290754,0.00003960864,0.00007506238,0.03766523,0.000004281829,0.001049876,0.1922789,0.003828801,0.4939803],"study_design_scores_gemma":[0.0007532648,0.0001953837,0.5626624,0.00009222743,0.000006708225,0.000001264438,0.162643,0.0003571564,0.0001405373,0.1976636,0.07510457,0.0003798154],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7889134,0.006173645,0.02666814,0.009709407,0.0009093469,0.002149588,0.00003808572,0.0002802859,0.1651581],"genre_scores_gemma":[0.972856,0.000469895,0.02423182,0.00008300212,0.0009176963,0.00003706403,0.00003908351,0.00001437983,0.001351042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4936005,"threshold_uncertainty_score":0.9986472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9296372523519871,"score_gpt":0.7377377898052143,"score_spread":0.1918994625467728,"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."}}