{"id":"W4409441986","doi":"10.1007/s10664-025-10655-9","title":"Predicting long time contributors with knowledge units of programming languages: an empirical study","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Empirical research; Programming language; Natural language processing; Data science; Artificial intelligence; Statistics; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007894702,0.000371083,0.000529593,0.0005264287,0.000126241,0.0001714494,0.001196456,0.0001540754,0.000009383289],"category_scores_gemma":[0.004101091,0.0003282413,0.00006980447,0.003440286,0.0000540887,0.0004776232,0.0005377164,0.0006004456,0.00001468885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002116057,"about_ca_system_score_gemma":0.0003136423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003118843,"about_ca_topic_score_gemma":0.00001316758,"domain_scores_codex":[0.9973222,0.0001273381,0.0004945934,0.000706501,0.0005837436,0.0007656083],"domain_scores_gemma":[0.9960057,0.002324192,0.00007401529,0.0008769675,0.0004225516,0.000296551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001512163,0.0004040338,0.9838823,0.0001295595,0.0001287445,0.00009131531,0.001905206,0.007397753,0.00003516854,0.00001646802,0.0001025798,0.005891766],"study_design_scores_gemma":[0.001398185,0.001041526,0.9392359,0.0004060762,0.000051082,0.00002670825,0.0002156054,0.05432653,0.001045753,0.000005730348,0.001660158,0.0005867286],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5913363,0.0002451727,0.406437,0.00003747397,0.0001100134,0.0004417564,0.000002928396,0.001373479,0.00001586647],"genre_scores_gemma":[0.975531,9.176234e-7,0.02400581,0.00002311786,0.00009296311,0.00009884936,0.000009874134,0.00005000396,0.0001875067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3841947,"threshold_uncertainty_score":0.999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01772367776384217,"score_gpt":0.3199314896089665,"score_spread":0.3022078118451244,"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."}}