{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002427921,0.001045639,0.0008280022,0.0007607387,0.0003682326,0.0008933638,0.002608445,0.001146483,0.001432808],"category_scores_gemma":[0.01075841,0.0004953251,0.0006475853,0.0003703271,0.001409911,0.001609307,0.001541265,0.00182393,0.0003862832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001235296,"about_ca_system_score_gemma":0.001823497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005804381,"about_ca_topic_score_gemma":0.005436498,"domain_scores_codex":[0.9983916,0.0006210216,0.00007072434,0.0003880876,0.0003749934,0.0001536249],"domain_scores_gemma":[0.9952365,0.00268006,0.0005579669,0.0007315867,0.0005599809,0.0002339389],"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":[0.0002262794,0.0003746632,0.005151615,0.0001255149,0.00008937561,0.0002518558,0.0002446911,0.7696744,0.01015208,0.005894975,0.00174162,0.206073],"study_design_scores_gemma":[0.00001396546,0.0000606625,0.0001966732,0.000005140007,0.000009597084,0.00003104957,0.0000120967,0.9948684,0.001548824,0.002917795,0.0003284157,0.000007299462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04034735,0.0001607988,0.9523779,0.0004123902,0.00003478771,0.0001332971,0.00004748236,0.005075208,0.001410762],"genre_scores_gemma":[0.8347521,0.0000675046,0.1630792,0.0002770414,0.00002656009,0.0002132439,0.00009057691,0.0002011473,0.001292583],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005804381,"threshold_uncertainty_score":0.01284021,"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."}}