{"id":"W2099083511","doi":"10.1145/1449715.1449736","title":"Is the sky pure today? AwkChecker","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Collocation (remote sensing); Computer science; Set (abstract data type); Natural language processing; Interface (matter); Word (group theory); Artificial intelligence; Linguistics; Programming language; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001177206,0.00008187494,0.00006549808,0.00003031944,0.0001856627,0.00007719122,0.001177274,0.00004968292,0.0000818957],"category_scores_gemma":[0.00002782646,0.00004346859,0.00004345438,0.0002857103,0.00005762026,0.0003191619,0.0002725327,0.0001514565,0.000103667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001397185,"about_ca_system_score_gemma":0.00003753244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003038427,"about_ca_topic_score_gemma":0.000003080231,"domain_scores_codex":[0.9993042,0.00001990973,0.00009102699,0.0002050617,0.0002138951,0.0001659317],"domain_scores_gemma":[0.9992896,0.00003404297,0.00003109575,0.0005540985,0.00005800094,0.0000332109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002937915,0.00005110979,0.001216723,0.00001162815,0.00001771159,0.0001056653,0.00457566,5.132578e-7,0.002961998,0.461098,0.4605887,0.06936936],"study_design_scores_gemma":[0.0003512249,0.0001186916,0.002283484,0.00004513616,0.000009407824,0.0009051414,0.00006690938,0.01131558,0.4927887,0.3100795,0.181231,0.000805302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006287007,0.003125816,0.9307162,0.03484612,0.0002017208,0.0001938471,7.462803e-7,0.001843398,0.02278518],"genre_scores_gemma":[0.5094658,0.00002360182,0.4743835,0.008457926,0.00005811143,0.000008778707,3.009364e-7,0.000005652682,0.007596354],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5031787,"threshold_uncertainty_score":0.2187688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02042356425322616,"score_gpt":0.2679772891031445,"score_spread":0.2475537248499183,"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."}}