{"id":"W6910333511","doi":"10.48448/fh9v-wv15","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","year":2022,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"USable; Audit; Quality (philosophy); Data quality; Natural language; Baseline (sea)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05674798,0.001626799,0.001156272,0.01515529,0.003820333,0.007908878,0.003482595,0.001595997,0.002161346],"category_scores_gemma":[0.1707065,0.001770006,0.001201378,0.01602943,0.003510099,0.007281967,0.007429428,0.003275496,0.006209167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002228949,"about_ca_system_score_gemma":0.006589975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02490279,"about_ca_topic_score_gemma":0.03936422,"domain_scores_codex":[0.920731,0.01978229,0.01151223,0.008801496,0.03731288,0.001860024],"domain_scores_gemma":[0.6265647,0.0766165,0.02009305,0.1233449,0.1467015,0.00667943],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001430139,0.0008752691,0.1406209,0.00351557,0.0008207852,0.001848417,0.01205358,0.003015438,0.02489752,0.005366579,0.5148012,0.2907546],"study_design_scores_gemma":[0.0002917045,0.0004553586,0.244883,0.002039231,0.0004407167,0.001889591,0.005257202,0.02410243,0.05775383,0.005331458,0.6569364,0.0006190388],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4540754,0.007022883,0.07608099,0.01445701,0.00289782,0.002952891,0.2339784,0.1639867,0.04454788],"genre_scores_gemma":[0.2450676,0.001934769,0.1514255,0.003274738,0.0004171329,0.002066447,0.5356425,0.04192058,0.01825077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.943252,"threshold_uncertainty_score":0.3001156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08150692081370468,"score_gpt":0.4195646770589851,"score_spread":0.3380577562452804,"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."}}