{"id":"W2934046129","doi":"10.2478/jos-2019-0007","title":"An Evolutionary Schema for Using “it-is-what-it-is” Data in Official Statistics","year":2019,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada","funders":"","keywords":"Data science; Schema (genetic algorithms); Computer science; Set (abstract data type); Big data; Agency (philosophy); Process (computing); Data mining; Information retrieval; Sociology; Social science","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":[0.006157867,0.0002464796,0.0006951622,0.0004722765,0.0001919399,0.0007018609,0.002189433,0.0001392393,0.0009098162],"category_scores_gemma":[0.004153676,0.0002208829,0.00008177965,0.0005337969,0.0001470569,0.002068026,0.0004614216,0.000359168,0.0001240318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001875654,"about_ca_system_score_gemma":0.0009848382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001103165,"about_ca_topic_score_gemma":0.0005898482,"domain_scores_codex":[0.9939772,0.000312271,0.00225359,0.0005497779,0.00243737,0.0004697359],"domain_scores_gemma":[0.9938514,0.002159624,0.001496309,0.001115811,0.001148934,0.0002279689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00092266,0.0009422553,0.0009819509,0.00009058269,0.0001047977,0.0001183645,0.001359816,0.003834347,0.000114893,0.04290622,0.8824742,0.06614987],"study_design_scores_gemma":[0.002490888,0.001169789,0.00334232,0.0002411538,0.0001979265,0.00004397131,0.01080224,0.4374886,0.00005531414,0.09223348,0.4513006,0.0006336812],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01148336,0.0001333379,0.9682086,0.001838711,0.002619538,0.0004382275,0.01512471,0.000007211541,0.0001462807],"genre_scores_gemma":[0.09019985,0.0002729292,0.8973669,0.008431269,0.001868624,0.000002717631,0.001018357,0.00007352125,0.000765849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4336543,"threshold_uncertainty_score":0.9961849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3369684994523318,"score_gpt":0.4966412882000322,"score_spread":0.1596727887477005,"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."}}