{"id":"W105148950","doi":"10.1002/j.1839-4655.2014.tb00322.x","title":"Evidence for the use of an algorithm in resolving inconsistent and missing Indigenous status in administrative data collections","year":2014,"lang":"en","type":"article","venue":"Australian Journal of Social Issues","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research","funders":"NSW Ministry of Health","keywords":"Indigenous; Missing data; Identification (biology); Life expectancy; Project commissioning; Consistency (knowledge bases); Data quality; Linkage (software); Publishing; Computer science; Data science; Data mining; Demography; Sociology; Political science; Operations management; Engineering; Machine learning; Artificial intelligence; Population","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":[],"consensus_categories":[],"category_scores_codex":[0.00218288,0.00006590099,0.0002365272,0.0001429589,0.0005969924,0.0002594331,0.000316239,0.00004182078,0.00001167782],"category_scores_gemma":[0.001625355,0.00005290042,0.00004308825,0.0003725378,0.0003105951,0.001027548,0.00004870478,0.0001585999,7.185662e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005630289,"about_ca_system_score_gemma":0.0002695341,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01065089,"about_ca_topic_score_gemma":0.03191723,"domain_scores_codex":[0.998522,0.000473981,0.0004263227,0.0001231643,0.0002328937,0.0002216199],"domain_scores_gemma":[0.9982225,0.001122585,0.0003485346,0.0001177971,0.0001082594,0.00008034248],"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":[0.0001804372,0.0003675373,0.07049808,0.00005935772,0.0002343178,0.00003599015,0.4136038,0.0001574479,0.0006496247,0.00175487,0.002148201,0.5103104],"study_design_scores_gemma":[0.001774095,0.001190305,0.540624,0.001898612,0.0004928793,0.00001763428,0.3186528,0.004742146,0.000435365,0.008139626,0.1214108,0.0006216963],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901937,0.000808716,0.001659364,0.006416038,0.0001864625,0.0004407784,0.0001684793,0.000006271026,0.0001201781],"genre_scores_gemma":[0.9860587,0.0004832223,0.01290013,0.00002646998,0.00024738,0.000001806944,0.000005570186,0.000005175287,0.0002715346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5096887,"threshold_uncertainty_score":0.9959373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3896094153131164,"score_gpt":0.4706682045091592,"score_spread":0.08105878919604281,"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."}}