{"id":"W3173944821","doi":"10.1145/3463274.3463343","title":"Assessing Developer Expertise from the Statistical Distribution of Programming Syntax Patterns","year":2021,"lang":"en","type":"article","venue":"Evaluation and Assessment in Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Task (project management); Syntax; Context (archaeology); Software engineering; Programming language; Data science; Artificial intelligence; Systems engineering; Engineering","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":[0.0009116319,0.0001255537,0.0001554704,0.00004788784,0.00005968846,0.0002876234,0.0002189904,0.00005009436,0.00002987278],"category_scores_gemma":[0.002833831,0.0001098744,0.00002389647,0.0003789205,0.00001688169,0.000460675,0.0001977194,0.0002622318,9.804618e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002152521,"about_ca_system_score_gemma":0.0002996794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005496631,"about_ca_topic_score_gemma":0.000009153246,"domain_scores_codex":[0.9983605,0.0001413335,0.0002974549,0.0003119064,0.0006581028,0.0002307383],"domain_scores_gemma":[0.9975048,0.001893013,0.00004680602,0.0002913279,0.0002044666,0.00005958256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001474554,0.00008931311,0.529316,0.00008037576,0.00004002789,0.0000323475,0.0009094105,0.01206395,0.000830021,0.002293467,0.00003943738,0.4543042],"study_design_scores_gemma":[0.0002528565,0.000008931171,0.7695247,0.0001716332,0.000007360173,0.000004820914,0.0001188647,0.2287484,0.0007885715,0.00005780894,0.0002003354,0.000115688],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3549183,0.0002473922,0.6443598,0.0001339618,0.0001320787,0.000127998,0.000009870624,0.00006906305,0.000001567456],"genre_scores_gemma":[0.8020954,0.00002097261,0.1976462,0.00001430143,0.00002822001,0.00007353647,0.0001101191,0.000009518681,0.00000181103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4541885,"threshold_uncertainty_score":0.448055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04264145128656933,"score_gpt":0.357883313491921,"score_spread":0.3152418622053517,"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."}}