{"id":"W7135689794","doi":"","title":"Data cleaning; is it time to stop sweeping it under the carpet?:An example from the Dogslife project","year":2017,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Process (computing); Software; Population; Data quality; Decimal; Quality (philosophy)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1734052,0.001614875,0.001849921,0.004757161,0.003465516,0.00600636,0.003852099,0.00316782,0.008824353],"category_scores_gemma":[0.272516,0.001040889,0.002576005,0.009812883,0.003238254,0.004802673,0.007141494,0.005070031,0.008808427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002260637,"about_ca_system_score_gemma":0.01084838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01002091,"about_ca_topic_score_gemma":0.01236458,"domain_scores_codex":[0.8431517,0.106173,0.01384757,0.008573523,0.02660643,0.001647868],"domain_scores_gemma":[0.7037275,0.1452226,0.0155153,0.05704263,0.07317179,0.005320148],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001247722,0.000330715,0.02164336,0.004830126,0.0007964093,0.0007551291,0.008707632,0.001097842,0.002549554,0.008617133,0.4976752,0.4517491],"study_design_scores_gemma":[0.0002651293,0.000537259,0.02934609,0.006111959,0.0003360385,0.0009729561,0.003425668,0.001806582,0.004420723,0.01681486,0.935662,0.0003007875],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06516384,0.02933938,0.5011122,0.2397432,0.009318026,0.01069394,0.07747656,0.02331539,0.04383731],"genre_scores_gemma":[0.07781738,0.0139368,0.7743225,0.04166748,0.001552045,0.01038714,0.05114587,0.01410478,0.01506597],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8265948,"threshold_uncertainty_score":0.9170656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9451241156580988,"score_gpt":0.5706476374828171,"score_spread":0.3744764781752817,"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."}}