{"id":"W2510461200","doi":"10.18653/v1/w16-0529","title":"Combining Off-the-shelf Grammar and Spelling Tools for the Automatic Evaluation of Scientific Writing (AESW) Shared Task 2016","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"Spelling; Computer science; Task (project management); Grammar; Natural language processing; Sentence; Artificial intelligence; Recall; Binary number; Binary classification; Linguistics; Arithmetic","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":[0.0051226,0.00009728859,0.000123959,0.00006180673,0.000368783,0.0005703756,0.0006873684,0.00003247714,0.00002524607],"category_scores_gemma":[0.0007334621,0.00004728354,0.00004888995,0.0001962445,0.000108375,0.0006484457,0.000210136,0.00004569928,0.000009651861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000348725,"about_ca_system_score_gemma":0.0001344255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001282995,"about_ca_topic_score_gemma":0.000009645948,"domain_scores_codex":[0.9983975,0.0001062296,0.000376181,0.0003427106,0.0005317396,0.0002456128],"domain_scores_gemma":[0.9970258,0.001782384,0.0001717599,0.0006314223,0.0003519912,0.00003660233],"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":[0.000001388233,0.00000995134,0.0001259932,0.0000220273,0.00001533182,1.063355e-7,0.0007545883,0.0003201163,0.006767001,0.02675458,0.0002547183,0.9649742],"study_design_scores_gemma":[0.0005192621,0.00001998416,0.0004690786,0.0001171395,0.0000276018,0.000003070094,0.0001361006,0.985287,0.002167961,0.01073601,0.0004308921,0.00008592993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1333177,0.0003768105,0.8627052,0.002131752,0.0003721547,0.0006581532,0.000003602907,0.00006747595,0.0003670963],"genre_scores_gemma":[0.9566241,0.000009218241,0.0428925,0.00006127102,0.00004938513,0.00003953464,0.000001210947,0.000007063547,0.0003157125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9849669,"threshold_uncertainty_score":0.5500146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08630704066969959,"score_gpt":0.2978033616651666,"score_spread":0.2114963209954671,"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."}}