{"id":"W4307407759","doi":"10.1162/99608f92.13e1d60e","title":"The Use of Data Science in a National Statistical Office","year":2022,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Data science; Computer science","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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02344427,0.000129059,0.0002972903,0.0003094508,0.001021791,0.000716537,0.03529165,0.000008249886,0.0001816653],"category_scores_gemma":[0.01055081,0.0000927673,0.00002135665,0.009609573,0.001932778,0.01561365,0.03012978,0.0002524861,0.0001620985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001978013,"about_ca_system_score_gemma":0.004095063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001518646,"about_ca_topic_score_gemma":0.00007364167,"domain_scores_codex":[0.992788,0.0003231901,0.0007031405,0.001548355,0.004092944,0.0005444046],"domain_scores_gemma":[0.9898822,0.001019931,0.0003475378,0.008180021,0.0004026288,0.0001676646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009065026,0.0002519139,0.0006481833,0.0003156221,0.00001531006,0.00003698084,0.00006783066,0.0002040997,0.0004850687,0.4901627,0.1639879,0.3438154],"study_design_scores_gemma":[0.00005752272,0.00001669986,0.001741486,0.0001329102,0.00001246928,0.00003052592,0.00000733566,0.2161016,0.000004982679,0.000184643,0.7815948,0.0001150426],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006442209,0.02244198,0.9086236,0.02025857,0.002729475,0.004388968,0.03681201,0.0003021474,0.003799069],"genre_scores_gemma":[0.0461474,0.0802732,0.857308,0.01159403,0.0001065695,0.0002032689,0.004095652,0.00003635579,0.0002354696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6176069,"threshold_uncertainty_score":0.9981545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2546039632704132,"score_gpt":0.3974377244224109,"score_spread":0.1428337611519977,"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."}}