{"id":"W2344444819","doi":"10.1145/2902362","title":"On the naturalness of software","year":2016,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Software Engineering Research","field":"Computer Science","cited_by":291,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Engineering and Physical Sciences Research Council","keywords":"Naturalness; Computer science; Natural language; Natural (archaeology); Software; Artificial intelligence; Program comprehension; Natural language processing; Simplicity; Code (set theory); Programming language; Linguistics; Software system; Set (abstract data type); Epistemology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.007878223,0.0007100564,0.0007565708,0.002499955,0.002791858,0.007357979,0.001861116,0.002879716,0.003580762],"category_scores_gemma":[0.05834256,0.000902481,0.0008043867,0.001959777,0.01979394,0.01673961,0.003293452,0.004313029,0.0008482643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002436539,"about_ca_system_score_gemma":0.002478671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005746363,"about_ca_topic_score_gemma":0.003595029,"domain_scores_codex":[0.9846436,0.007381175,0.001033984,0.003001132,0.003515805,0.000424319],"domain_scores_gemma":[0.9151634,0.06703555,0.003973648,0.008389581,0.004450383,0.0009875688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009211133,0.00006342032,0.00540392,0.000253438,0.00002968558,0.0002545333,0.004354045,0.007362431,0.001607774,0.9370254,0.004947805,0.03860548],"study_design_scores_gemma":[0.00001298246,0.00004779833,0.002819508,0.0001492934,0.00001192493,0.0004260349,0.0009425919,0.0219327,0.0007132613,0.9463188,0.0265845,0.00004051164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1999529,0.01238592,0.6270979,0.07718356,0.0007303439,0.0001978439,0.001735024,0.001583092,0.07913346],"genre_scores_gemma":[0.8765277,0.003876625,0.1056383,0.004733854,0.0008503463,0.0003793408,0.001388561,0.0006633641,0.005941921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9972081,"threshold_uncertainty_score":0.04166454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04508847840595311,"score_gpt":0.2959249936897846,"score_spread":0.2508365152838315,"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."}}