{"id":"W4403640797","doi":"10.1007/978-3-031-71975-2_4","title":"Fairness Analysis of Machine Learning-Based Code Reviewer Recommendation","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Code (set theory); Information retrieval; Natural language processing; World Wide Web; Artificial intelligence; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03842275,0.0008568048,0.003059692,0.002948311,0.002707399,0.003884039,0.00565567,0.00276646,0.008553631],"category_scores_gemma":[0.1544716,0.0007586813,0.001277263,0.002852058,0.003042615,0.006503964,0.002612824,0.003250339,0.001099294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005816093,"about_ca_system_score_gemma":0.006152671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008927106,"about_ca_topic_score_gemma":0.006821441,"domain_scores_codex":[0.968173,0.02050226,0.0007846921,0.002178463,0.006161409,0.002200183],"domain_scores_gemma":[0.7179525,0.2390359,0.005506139,0.01652527,0.01774072,0.003239443],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001666957,0.0005467547,0.007836739,0.0002991638,0.0002579451,0.0002135379,0.0006870544,0.2432428,0.001686852,0.5997996,0.01769924,0.1260633],"study_design_scores_gemma":[0.00006454156,0.00009168116,0.001190216,0.00002783896,0.00005011492,0.00005749995,0.00007262211,0.8400975,0.0006414966,0.1563667,0.00130289,0.00003686924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1338801,0.0019428,0.8218725,0.00527913,0.0005812961,0.0005036163,0.0005298005,0.0005699845,0.03484062],"genre_scores_gemma":[0.915737,0.0004559677,0.06257658,0.0005060168,0.0007090986,0.0002309923,0.0002645339,0.0001800948,0.01933969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9615772,"threshold_uncertainty_score":0.2032014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0855545768711964,"score_gpt":0.4016284899061421,"score_spread":0.3160739130349458,"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."}}