{"id":"W4409495297","doi":"10.1109/icstw64639.2025.10962516","title":"Adaptive Test Healing using LLM/GPT and Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nutrasource","funders":"","keywords":"Reinforcement learning; Computer science; Test (biology); Reinforcement; Artificial intelligence; Engineering; Structural engineering; Biology","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":[0.0004798704,0.00007340087,0.0001222282,0.0001527446,0.0002599439,0.0001757042,0.0002461552,0.00003387686,0.00001826419],"category_scores_gemma":[0.0003486371,0.00006319552,0.00003931136,0.0005960011,0.00004536583,0.0002156928,0.0003988246,0.0001635262,0.000007169746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006418937,"about_ca_system_score_gemma":0.00009954072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003472645,"about_ca_topic_score_gemma":0.000009113406,"domain_scores_codex":[0.9990814,0.00005423569,0.0001636645,0.0002803495,0.0002050458,0.000215264],"domain_scores_gemma":[0.9991173,0.000481465,0.00002680664,0.0002198183,0.00009495985,0.0000596505],"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":[0.00002633864,0.0002833091,0.1020814,0.0002844532,0.0002546842,0.00003041556,0.002015199,0.3893387,0.003328935,0.1504251,0.0005244286,0.3514071],"study_design_scores_gemma":[0.0001159146,0.00006376122,0.0004748935,0.00004054511,0.000005038688,0.00000140457,0.0001234672,0.9960887,0.0008223967,0.001137979,0.001054298,0.00007153874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009240459,0.0002196668,0.9854503,0.0006059673,0.00002870892,0.00007558609,6.690419e-8,0.0001023891,0.004276854],"genre_scores_gemma":[0.9635686,0.00006129728,0.03398568,0.0002000008,0.00001295486,0.000003240855,4.203665e-7,0.000002189515,0.002165573],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9543282,"threshold_uncertainty_score":0.2577039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02888483881021119,"score_gpt":0.3116515862055184,"score_spread":0.2827667473953072,"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."}}