{"id":"W4220931242","doi":"10.15353/acmla.n170.4873","title":"OpenRefine: An Approachable Open Tool to Clean Research Data","year":2022,"lang":"en","type":"article","venue":"Bulletin - Association of Canadian Map Libraries and Archives (ACMLA)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Context (archaeology); Computer science; World Wide Web; Data science; Open data; Open source; Programming language; Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004285227,0.0001379437,0.0002363478,0.001086452,0.001528421,0.006328607,0.01043887,0.00003307984,0.0004910289],"category_scores_gemma":[0.001139793,0.0001545206,0.00002256277,0.001150087,0.00009003791,0.009485846,0.01758322,0.0004667639,0.00002514892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007765651,"about_ca_system_score_gemma":0.0007702225,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03548894,"about_ca_topic_score_gemma":0.01157154,"domain_scores_codex":[0.9957542,0.001322185,0.0003361859,0.0008907498,0.0009434136,0.0007532339],"domain_scores_gemma":[0.9962067,0.00100287,0.0002046826,0.002006182,0.00004256388,0.0005370016],"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":[0.00005140902,0.00006893414,0.001355455,0.00002526138,0.00005018898,0.00001723464,0.0008472329,0.00007388586,0.00002601251,0.6176234,0.3564488,0.02341215],"study_design_scores_gemma":[0.0003213608,0.000216735,0.005759169,0.00001045168,0.000003766724,0.000001444972,0.001472205,0.003098309,0.00002349158,0.004977857,0.9839249,0.0001902591],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.007340268,0.000393226,0.008689288,0.7127361,0.000490469,0.0038827,0.003100255,0.0001412662,0.2632264],"genre_scores_gemma":[0.103028,0.001537591,0.5551477,0.01353788,0.0005906813,0.001001617,0.0045799,0.0001615199,0.3204151],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.6991982,"threshold_uncertainty_score":0.9997715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1705571027230388,"score_gpt":0.3449695130579474,"score_spread":0.1744124103349087,"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."}}