{"id":"W3046721769","doi":"10.3233/sji-200658","title":"A vision on future advanced data collection","year":2020,"lang":"en","type":"article","venue":"Statistical Journal of the IAOS","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Data collection; Metadata; Confidentiality; Big data; Computer science; Data science; Data governance; Data quality; Process (computing); Business; Knowledge management; Marketing; World Wide Web; Data mining; Computer security; Sociology","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":[0.001854718,0.0000698675,0.0001847493,0.00004626999,0.0001323714,0.0001634194,0.001733714,0.00002488855,0.0003965358],"category_scores_gemma":[0.007497913,0.00003513281,0.00005056159,0.0004197298,0.00006217755,0.0003343035,0.0004931351,0.0002511265,0.0001399303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002066148,"about_ca_system_score_gemma":0.00007509548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002202556,"about_ca_topic_score_gemma":0.000009139095,"domain_scores_codex":[0.9973008,0.0003750908,0.0005391627,0.0002052566,0.001472121,0.0001075727],"domain_scores_gemma":[0.997826,0.0009883032,0.0003441622,0.0005590375,0.0001441367,0.0001383136],"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":[0.0004450563,0.0000636149,0.00002130391,0.000005339147,0.00001945479,0.00002675069,0.0001797575,0.0001429432,0.0001144639,0.02478231,0.7227824,0.2514167],"study_design_scores_gemma":[0.0008663097,0.0008457606,0.00566895,0.0000403799,0.0000458627,0.00002109305,0.00109898,0.007253422,0.0001044817,0.07423116,0.9097201,0.0001034497],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00441365,0.0001396341,0.7662852,0.2208409,0.003545247,0.0003414306,0.0008817638,0.00001664481,0.003535524],"genre_scores_gemma":[0.9045196,0.0001810925,0.06920966,0.02280322,0.001915043,0.000001864095,0.00003573105,0.00002352,0.001310271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.900106,"threshold_uncertainty_score":0.8976244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2210306705076511,"score_gpt":0.470280161569638,"score_spread":0.2492494910619869,"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."}}