{"id":"W4390411712","doi":"10.1007/s10664-023-10421-9","title":"Using knowledge units of programming languages to recommend reviewers for pull requests: an empirical study","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Baseline (sea); Operationalization; Code (set theory); Java; Task (project management); Recommender system; Artificial intelligence; Range (aeronautics); Code review; Information retrieval; Machine learning; Programming language; Natural language processing; Set (abstract data type); Software; Software quality; Software development; 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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00162014,0.0003419316,0.0005379472,0.0006769534,0.0001198239,0.0001366377,0.001193627,0.0001280367,0.00000527019],"category_scores_gemma":[0.009665093,0.0003411928,0.000112748,0.004591008,0.0000210268,0.0004085203,0.0005916898,0.0003430562,0.00002755794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002423238,"about_ca_system_score_gemma":0.0001533377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002489637,"about_ca_topic_score_gemma":0.000007713755,"domain_scores_codex":[0.9971744,0.0001214401,0.0005739108,0.0007485375,0.0005008915,0.0008807536],"domain_scores_gemma":[0.9959971,0.002162385,0.00006808074,0.0009115085,0.0003990992,0.0004618835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005960845,0.001362175,0.697902,0.002129453,0.0003454754,0.0002386032,0.02187296,0.1041553,0.001321333,0.0001340427,0.01184598,0.1586331],"study_design_scores_gemma":[0.003821066,0.006560785,0.3306936,0.002253542,0.0001820561,0.0001072059,0.00173826,0.3884089,0.004656292,0.0001481615,0.2569258,0.00450432],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4744594,0.0002828169,0.5218954,0.0001572218,0.000366873,0.001061466,0.000009432938,0.001764349,0.000003094582],"genre_scores_gemma":[0.5647064,0.00001236954,0.4340232,0.00009719787,0.0003908398,0.0004674545,0.00002894307,0.0001630257,0.0001105854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3672084,"threshold_uncertainty_score":0.999904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1512106083127953,"score_gpt":0.4371718466402538,"score_spread":0.2859612383274585,"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."}}