{"id":"W4299786231","doi":"10.48550/arxiv.1704.03397","title":"Debugging Behaviour of Embedded-Software Developers: An Exploratory\\n Study","year":2017,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Debugging; Algorithmic program debugging; Computer science; Programming language; Software engineering; Software; Software bug; Exploratory research","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":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.00260804,0.001171693,0.001682368,0.0006887955,0.001481126,0.0005233534,0.008478614,0.001176816,0.0001000475],"category_scores_gemma":[0.0003455312,0.001282093,0.0006156581,0.0009703012,0.0007020928,0.003768079,0.005973643,0.001847807,0.0001975385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006267892,"about_ca_system_score_gemma":0.002267694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006470536,"about_ca_topic_score_gemma":0.0006565865,"domain_scores_codex":[0.992327,0.001025122,0.001220069,0.003780759,0.000542639,0.001104364],"domain_scores_gemma":[0.987285,0.0002169335,0.002020797,0.008055534,0.001715644,0.0007060997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001881115,0.002736541,0.9214278,0.0006164623,0.000504438,0.0008878199,0.02263935,0.04424167,0.00001199485,0.0008443812,0.00006100783,0.005840359],"study_design_scores_gemma":[0.0102459,0.005340773,0.6012011,0.004458794,0.002919014,0.00009629613,0.04555241,0.3108326,0.001487621,0.008412566,0.0004141209,0.009038894],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8501665,0.0001291758,0.1445483,0.00001470257,0.002799079,0.001636286,0.00003902171,0.0004606496,0.0002062481],"genre_scores_gemma":[0.9967085,0.0001715831,0.002265529,0.00002939538,0.0001855607,0.00001000639,0.00002025746,0.00007315357,0.0005360191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3202268,"threshold_uncertainty_score":0.9998188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1073422640600282,"score_gpt":0.2346379450917591,"score_spread":0.127295681031731,"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."}}