{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007178848,0.0008664907,0.001742762,0.0006833816,0.001031105,0.02463821,0.01978722,0.000643882,0.0005610415],"category_scores_gemma":[0.008431799,0.0006635574,0.0003444259,0.0008904537,0.0002001446,0.004087115,0.03872478,0.0008610364,0.0003109369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002594287,"about_ca_system_score_gemma":0.001110635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002838809,"about_ca_topic_score_gemma":0.0001856702,"domain_scores_codex":[0.9892733,0.001209747,0.002907007,0.003389917,0.002359834,0.0008602488],"domain_scores_gemma":[0.9852051,0.003998858,0.003165986,0.006216902,0.0009933402,0.0004198757],"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":[0.0005026866,0.0001924013,0.01721279,0.0004664462,0.0001742552,0.000172348,0.0001107766,0.001005593,0.0003074644,0.0001535381,0.9716377,0.008064053],"study_design_scores_gemma":[0.00321408,0.0002548491,0.07625815,0.002316494,0.0003958177,0.00007145351,0.0002804964,0.05629149,0.001477392,0.009772042,0.8473597,0.002308086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2915374,0.005193754,0.02163726,0.01600021,0.06688587,0.06992038,0.1417549,0.006677345,0.3803929],"genre_scores_gemma":[0.7199289,0.0001624325,0.04021418,0.009304158,0.002995356,0.007038997,0.08567151,0.0006439381,0.1340405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4283915,"threshold_uncertainty_score":0.9999206,"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."}}