{"id":"W4400680859","doi":"10.1109/saner60148.2024.00057","title":"Comparative Study of Reinforcement Learning in GitHub Pull Request Outcome Predictions","year":2024,"lang":"en","type":"article","venue":"","topic":"Interconnection Networks and Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Outcome (game theory); Reinforcement; Artificial intelligence; Engineering; Structural engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003931778,0.00007777028,0.0001841418,0.0001847115,0.00005281101,0.0001116948,0.000209342,0.00002614228,0.00003975415],"category_scores_gemma":[0.000008274449,0.00006095598,0.00003697021,0.0004634086,0.00001096572,0.0003129141,0.00009153201,0.0001805771,0.00003479777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006054152,"about_ca_system_score_gemma":0.00002357334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004711591,"about_ca_topic_score_gemma":0.0005502675,"domain_scores_codex":[0.9989338,0.00009839917,0.0004451207,0.0002189785,0.0001779252,0.0001257628],"domain_scores_gemma":[0.9995965,0.00008091697,0.0000480973,0.0001920029,0.00005392009,0.00002856644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001076873,0.0003363831,0.0378575,0.00006318062,0.0001316191,0.00004023696,0.0425937,0.742853,0.0001072408,0.1711785,0.003793015,0.001034816],"study_design_scores_gemma":[0.0001948139,0.0005598128,0.002651675,0.00006278052,0.000003600733,0.000007092476,0.003211187,0.9906682,0.00004380409,0.00006909666,0.002449924,0.00007800538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1770003,0.00008139629,0.7588428,0.000217691,0.001728635,0.0005361052,3.063905e-7,0.0003547577,0.06123795],"genre_scores_gemma":[0.9934464,0.000001771081,0.0001955657,0.00001868366,0.00004986442,0.0000327865,7.497046e-7,0.000003161381,0.006251068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.816446,"threshold_uncertainty_score":0.2485713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05525781047448976,"score_gpt":0.3240587006938017,"score_spread":0.268800890219312,"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."}}