{"id":"W4390122176","doi":"10.5267/j.ijiec.2023.11.001","title":"Software testing and release decision at different statistical confidence levels with consideration of debuggers’ learning and negligent factors","year":2023,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Debugging; Reliability engineering; Software quality; Computer science; Software; Confidence interval; Resource (disambiguation); Process (computing); Imperfect; Function (biology); Risk analysis (engineering); Software development; Engineering; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01082442,0.0006243468,0.0006210015,0.00125853,0.0004795126,0.002158595,0.001098827,0.001429485,0.0009923172],"category_scores_gemma":[0.08380087,0.0004614792,0.0007325871,0.0005408548,0.001242436,0.002630485,0.001089017,0.001547871,0.0001071352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218949,"about_ca_system_score_gemma":0.001684037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003524569,"about_ca_topic_score_gemma":0.00247774,"domain_scores_codex":[0.9951018,0.001363175,0.0003537618,0.0007771326,0.001429949,0.0009741465],"domain_scores_gemma":[0.8975874,0.08031255,0.01039615,0.003282384,0.005920673,0.00250085],"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":[0.001579122,0.0005405333,0.2390284,0.0001825884,0.0002293344,0.001816035,0.001117138,0.6322412,0.009298041,0.02018437,0.0005586075,0.09322456],"study_design_scores_gemma":[0.00004053699,0.0007307086,0.06700858,0.00003777043,0.0001298975,0.0003234698,0.0006711709,0.9113816,0.007789762,0.01155629,0.0002362222,0.00009405781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9312934,0.0001636437,0.06675427,0.0003260413,0.000010657,0.00002689719,0.00003372714,0.0001001742,0.001291281],"genre_scores_gemma":[0.9969701,0.00002252294,0.00282951,0.00001275608,0.000003080577,0.000006280986,0.00001898194,0.000005304963,0.0001314284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01082442,"threshold_uncertainty_score":0.05724567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06123347903042183,"score_gpt":0.3108060944516885,"score_spread":0.2495726154212667,"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."}}