{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1811995,0.0006394638,0.002463077,0.003582651,0.003217596,0.004060063,0.002958448,0.003889059,0.001767761],"category_scores_gemma":[0.5553102,0.001159065,0.001160708,0.006575675,0.007251444,0.006346717,0.005316296,0.004255379,0.0002026275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002478938,"about_ca_system_score_gemma":0.004684114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005005651,"about_ca_topic_score_gemma":0.005165317,"domain_scores_codex":[0.7259731,0.2490119,0.005693189,0.006976666,0.0115578,0.0007872321],"domain_scores_gemma":[0.3056238,0.6421299,0.01706518,0.02446749,0.009769466,0.0009440961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000532302,0.0003859667,0.137188,0.00427311,0.002429044,0.001073697,0.01689847,0.0937411,0.001083178,0.512116,0.00678453,0.2234947],"study_design_scores_gemma":[0.0001495159,0.0006216357,0.02242873,0.0024502,0.0005164599,0.0007927401,0.00409503,0.1549721,0.001744057,0.7933903,0.01866411,0.0001751283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06528195,0.003475727,0.9174967,0.008413354,0.0002977509,0.00070326,0.0002592761,0.0001676258,0.003904391],"genre_scores_gemma":[0.682825,0.001872779,0.3099285,0.00280129,0.0003040543,0.001615971,0.0002021155,0.00008158763,0.0003687444],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1811995,"threshold_uncertainty_score":0.9582859,"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."}}