{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01653026,0.003488813,0.002062148,0.007307525,0.001122915,0.003039988,0.002475122,0.002814997,0.005092372],"category_scores_gemma":[0.06146045,0.001006276,0.001855781,0.00211294,0.0007798352,0.003794902,0.006829083,0.002442692,0.008282926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231879,"about_ca_system_score_gemma":0.003281657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004435483,"about_ca_topic_score_gemma":0.005710825,"domain_scores_codex":[0.9774333,0.009461634,0.00383776,0.004314426,0.00407026,0.0008826532],"domain_scores_gemma":[0.9438443,0.02686421,0.003122561,0.008543083,0.01541692,0.002208977],"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":[0.001489655,0.001534101,0.02009957,0.002369057,0.0006703302,0.001025102,0.002817946,0.01134745,0.08466695,0.00118771,0.09406548,0.7787267],"study_design_scores_gemma":[0.001966286,0.003312499,0.1082899,0.000798786,0.0006680533,0.003083513,0.003228236,0.4926732,0.2524706,0.01588145,0.1165723,0.001055326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4668785,0.002172848,0.3037581,0.001338942,0.002053056,0.003752708,0.03702114,0.1689503,0.0140745],"genre_scores_gemma":[0.6147305,0.0003647584,0.2968578,0.0005271521,0.0004072789,0.003339182,0.06634565,0.01050399,0.006923738],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01653026,"threshold_uncertainty_score":0.08742142,"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."}}