{"id":"W3032491810","doi":"","title":"GM-RKB WikiText Error Correction Task and Baselines.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Error detection and correction; Artificial intelligence; Natural language processing; Task (project management); Language model; Ground truth; Speech recognition; Information retrieval; Machine learning; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.01059755,0.003535073,0.001942068,0.003318715,0.002181076,0.00368667,0.004606127,0.004208244,0.02160893],"category_scores_gemma":[0.05372028,0.0009634225,0.001313136,0.00275908,0.001208548,0.005665122,0.00727488,0.00477811,0.03326852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111886,"about_ca_system_score_gemma":0.003411531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01392336,"about_ca_topic_score_gemma":0.01772046,"domain_scores_codex":[0.9870745,0.004811199,0.001703967,0.002943043,0.002779353,0.000688035],"domain_scores_gemma":[0.965261,0.01306785,0.001404442,0.01021427,0.008017174,0.002035249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005223535,0.003812697,0.007675368,0.004758002,0.0007832855,0.000609575,0.0009531707,0.005744122,0.02525153,0.002009973,0.6445594,0.2986194],"study_design_scores_gemma":[0.007347206,0.004299547,0.09471348,0.001924592,0.001967526,0.004745079,0.003159251,0.1546687,0.1674633,0.01371451,0.5449161,0.001080669],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2874857,0.007231971,0.08066499,0.003746382,0.007037636,0.006965436,0.2961319,0.212249,0.09848691],"genre_scores_gemma":[0.254823,0.0008243613,0.1135713,0.002143651,0.0005430844,0.006159883,0.5628424,0.01292921,0.04616315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02160893,"threshold_uncertainty_score":0.07228905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02172302327528814,"score_gpt":0.2949398695453348,"score_spread":0.2732168462700467,"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."}}