{"id":"W3119230199","doi":"10.1109/tse.2021.3107680","title":"Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results in the Space Domain","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"H2020 European Research Council; Natural Sciences and Engineering Research Council of Canada; European Commission; European Space Agency","keywords":"Computer science; Context (archaeology); Software construction; Software; Software system; Scalability; Software reliability testing; Software engineering; Verification and validation; Avionics software; Domain (mathematical analysis); Reliability engineering; Engineering; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008656675,0.0003018857,0.0004274985,0.0005958977,0.0002192921,0.0004886769,0.0005114279,0.0001986536,2.938698e-7],"category_scores_gemma":[0.0002256956,0.000279821,0.0002520395,0.001179145,0.00002891475,0.0001874641,0.00001931763,0.0006412293,8.419161e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001539377,"about_ca_system_score_gemma":0.00009135601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003467092,"about_ca_topic_score_gemma":0.00004951529,"domain_scores_codex":[0.998118,0.0001149924,0.0004077193,0.000696519,0.0003087584,0.0003540457],"domain_scores_gemma":[0.9969224,0.001874493,0.0001235457,0.0008842532,0.0001276075,0.00006763815],"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":[0.000006284068,0.00009484717,0.00002503226,0.0001438977,0.0001581571,0.00001791731,0.002094254,0.9954139,0.00001410636,0.0002945295,0.0001534374,0.001583646],"study_design_scores_gemma":[0.0003004716,0.00006670413,0.000626508,0.0004255034,0.000219137,0.0000332255,0.00007402532,0.9966145,0.0002457598,0.000911847,0.00008188339,0.000400455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01281132,0.0002063438,0.9823565,0.0002244595,0.0006319852,0.000527459,0.0000875925,0.003149069,0.00000524665],"genre_scores_gemma":[0.6927657,0.00001473435,0.3065873,0.00001909159,0.00005067496,0.0005068218,0.00002132935,0.00001999208,0.00001437848],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6799543,"threshold_uncertainty_score":0.9999654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02396113930530181,"score_gpt":0.2537868037006459,"score_spread":0.2298256643953441,"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."}}