{"id":"W7027998132","doi":"","title":"Documentation as Data Rescue: Restoring a Collection of Canadian Health Survey Files","year":2017,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Census and Population Estimation","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Government (linguistics); Census; Mandate; Documentation; Agency (philosophy); Data collection; Population; Health statistics; Statistics education; Survey data collection","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002106633,0.0001258079,0.0002900025,0.0005452778,0.001400441,0.00005114185,0.0007501838,0.000133464,0.0003436633],"category_scores_gemma":[0.001319041,0.0001648167,0.00005812196,0.0003408388,0.0001063654,0.001332762,0.0002344279,0.0001833731,0.00002468431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000311942,"about_ca_system_score_gemma":0.0004125637,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4889763,"about_ca_topic_score_gemma":0.8263625,"domain_scores_codex":[0.9985006,0.0002799218,0.0002738358,0.00031143,0.0003931524,0.0002410038],"domain_scores_gemma":[0.9974593,0.0001660824,0.0006863674,0.001232541,0.0002477982,0.0002079274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003496302,0.000104309,0.9723368,0.0002223367,0.0001114074,0.000009724506,0.00402627,0.00005406934,0.0006020778,0.005044173,0.01455349,0.00258573],"study_design_scores_gemma":[0.0007192468,0.00007129183,0.9948731,0.000135948,0.0000340933,0.000004901062,0.000274254,0.0002397721,0.0001946515,0.002240137,0.001072915,0.0001396632],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99637,0.00003713482,0.0001158901,0.001020895,0.0002001013,0.0002962134,0.0005057231,0.00002407376,0.001429971],"genre_scores_gemma":[0.9932723,0.00006382717,0.003934509,0.00001948184,0.00002992873,1.885708e-7,0.0007212188,0.00001593648,0.001942629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3373862,"threshold_uncertainty_score":0.9998996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2059497497906848,"score_gpt":0.3681987497418944,"score_spread":0.1622489999512096,"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."}}