{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004935308,0.0001087402,0.0001119791,0.00005754086,0.0001140357,0.0001986259,0.0001664919,0.00006400943,0.00003484947],"category_scores_gemma":[0.000263171,0.00009067075,0.00001976035,0.0002433908,0.00003124597,0.000327046,0.0001299405,0.0001191366,0.000005391306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001772309,"about_ca_system_score_gemma":0.00001763916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009913586,"about_ca_topic_score_gemma":0.00001796087,"domain_scores_codex":[0.9989866,0.0001068093,0.0001406548,0.0003286727,0.0003086669,0.0001286128],"domain_scores_gemma":[0.9995329,0.00005897475,0.00008398385,0.0001535848,0.00008066073,0.00008986126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002114295,0.00001307099,0.0003376231,0.00005748226,0.000009670541,0.0000100737,0.02381738,0.00004586246,0.01130109,0.0002791968,0.002762098,0.9613453],"study_design_scores_gemma":[0.0004609516,0.0001525678,0.001423124,0.00006755063,0.00003851197,0.00004290437,0.001052448,0.9863434,0.004472841,0.001069308,0.004614589,0.0002618301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7818754,0.04119306,0.168043,0.006573515,0.0002654354,0.0005407762,0.000004727102,0.0007315506,0.0007725139],"genre_scores_gemma":[0.9664814,0.00004863643,0.0319698,0.00120481,0.000183556,0.00001460767,0.00001592437,0.000008372092,0.00007283807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9862975,"threshold_uncertainty_score":0.3697446,"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."}}