{"id":"W4386140507","doi":"10.1007/s10664-023-10363-2","title":"A comparison of reinforcement learning frameworks for software testing tasks","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Regression testing; Software performance testing; Software engineering; System integration testing; Software reliability testing; Software development; Adaptation (eye); Context (archaeology); Test strategy; Reinforcement learning; Software inspection; Manual testing; Software testing; Software construction; Machine learning; Software; Software quality; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005765295,0.0002691385,0.0004463816,0.0003029112,0.0001909661,0.00009405167,0.0007281156,0.0002742961,0.000003558172],"category_scores_gemma":[0.01792244,0.0002757741,0.0001459881,0.00152879,0.00002903835,0.0001972463,0.0004262977,0.000670963,0.00001582143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007935562,"about_ca_system_score_gemma":0.0000638294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001464527,"about_ca_topic_score_gemma":2.31527e-7,"domain_scores_codex":[0.9979228,0.00002770915,0.0005696762,0.0004646314,0.0004030063,0.0006121518],"domain_scores_gemma":[0.9940146,0.0049387,0.000187597,0.0004905515,0.0002180397,0.0001504809],"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":[0.000006527179,0.0000453128,0.3459564,0.0002985103,0.00003686968,0.000009685733,0.0009760349,0.5896881,0.0001165094,0.0001901652,0.01315977,0.04951609],"study_design_scores_gemma":[0.000247855,0.0003686287,0.01604009,0.0004306706,0.00001432024,0.000007628992,0.000008849095,0.9749947,0.001223372,0.002333176,0.003873684,0.0004570255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0144624,0.0001077381,0.9581695,0.0001160922,0.000300686,0.0002686941,0.000001863654,0.0265605,0.00001258308],"genre_scores_gemma":[0.448393,0.000001263909,0.5512787,0.00006548847,0.00007747795,0.00009163663,0.00001284537,0.00003470445,0.00004486924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4339306,"threshold_uncertainty_score":0.9999694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06973939181903052,"score_gpt":0.3503954270661822,"score_spread":0.2806560352471517,"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."}}