{"id":"W2922217177","doi":"10.13016/m231pw-vd2z","title":"RESTORE: Automated Regression Testing for Datasets","year":2019,"lang":"en","type":"preprint","venue":"Maryland Shared Open Access Repository (USMAI Consortium)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Set (abstract data type); Data mining; Process (computing); Scale (ratio); Quality (philosophy); Data set; Data quality; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.007557856,0.001677476,0.0008494241,0.003448818,0.0005124909,0.001529653,0.002814151,0.001103608,0.005551855],"category_scores_gemma":[0.04831599,0.0008181125,0.00165694,0.001837785,0.001023069,0.002149624,0.002200301,0.001694826,0.002984696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005168762,"about_ca_system_score_gemma":0.001593363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002914566,"about_ca_topic_score_gemma":0.003547882,"domain_scores_codex":[0.9921669,0.002978326,0.0008376027,0.001522006,0.00216206,0.0003330714],"domain_scores_gemma":[0.9695114,0.02005104,0.001736192,0.006251653,0.002109785,0.000340002],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00108331,0.0006004289,0.04861316,0.001135279,0.0007171265,0.001074327,0.0007626412,0.1414051,0.02422266,0.008737148,0.129764,0.6418847],"study_design_scores_gemma":[0.0003610569,0.0003439451,0.01315375,0.000108924,0.00008999775,0.0005812135,0.0001945381,0.9148148,0.03323948,0.01642095,0.02060344,0.00008797333],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0859937,0.0004791528,0.4947439,0.0009137464,0.0002308439,0.000360354,0.00830132,0.4061981,0.0027789],"genre_scores_gemma":[0.4164039,0.0002697074,0.5369196,0.0006715416,0.0001480998,0.0007892619,0.0232054,0.01847569,0.003116827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9924421,"threshold_uncertainty_score":0.03997022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3693561605413949,"score_gpt":0.5077334092430275,"score_spread":0.1383772487016326,"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."}}