{"id":"W1714170610","doi":"","title":"Grammaticality Judgement in a Word Completion Task","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital","funders":"","keywords":"Computer science; Grammaticality; Natural language processing; Syntax; Word (group theory); Judgement; Task (project management); Artificial intelligence; Usability; Grammar; Linguistics; Human–computer interaction","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":[0.0004966114,0.00009774044,0.0002118457,0.00008145581,0.00008914777,0.00004400143,0.0004503589,0.0000298496,0.000001411225],"category_scores_gemma":[0.002423397,0.00008511194,0.0001037844,0.0003418647,0.00006686992,0.00002987598,0.00009364848,0.0001402546,0.000007088249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009390009,"about_ca_system_score_gemma":0.00007220927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763004,"about_ca_topic_score_gemma":0.0007867665,"domain_scores_codex":[0.9986594,0.00005001654,0.0004335835,0.0001942403,0.0004757794,0.000187029],"domain_scores_gemma":[0.9978114,0.0005487399,0.0006395279,0.0002399769,0.0007089904,0.00005140094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002050356,0.0001391647,0.5738457,0.00002614773,0.00004225856,4.677118e-7,0.0003267949,0.00972833,0.00003442204,0.4102695,0.0003059352,0.005260811],"study_design_scores_gemma":[0.0004534197,0.00005243469,0.8679803,0.000008520243,0.00001099664,5.570637e-7,0.00001058921,0.09070626,0.00003039937,0.03189367,0.008714848,0.0001379962],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4517892,0.00000726534,0.536243,0.002256319,0.004860328,0.001225759,0.0002454997,0.0001262511,0.003246426],"genre_scores_gemma":[0.9542439,3.79538e-7,0.04523589,0.0002225377,0.0002101369,0.00001802755,0.00003561027,0.000006026038,0.0000275092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5024547,"threshold_uncertainty_score":0.3470764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01283611387327251,"score_gpt":0.2508910349973942,"score_spread":0.2380549211241217,"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."}}