{"id":"W2922606767","doi":"10.1109/icpc.2019.00020","title":"An Empirical Study on Practicality of Specification Mining Algorithms on a Real-World Application","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Computer science; Program comprehension; Context (archaeology); Implementation; Inference; Programming language; Abstraction; Set (abstract data type); Software engineering; Root cause; Software; Algorithm; Artificial intelligence; Software system; Reliability engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0278858,0.0009369105,0.0006861211,0.002875826,0.0008943356,0.002397574,0.002036777,0.002053047,0.002187308],"category_scores_gemma":[0.3244731,0.0005758698,0.001030965,0.0038585,0.002276103,0.005503675,0.001697818,0.003241859,0.0009768747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001457418,"about_ca_system_score_gemma":0.0009365113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001637026,"about_ca_topic_score_gemma":0.001751635,"domain_scores_codex":[0.972109,0.01531495,0.002781889,0.003706739,0.005338357,0.0007490599],"domain_scores_gemma":[0.4286365,0.5090995,0.01361146,0.03074149,0.0157371,0.002174077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004869211,0.006894337,0.5054127,0.002454752,0.0009329803,0.0007687566,0.005645175,0.1004267,0.008676514,0.007035826,0.01114448,0.3457387],"study_design_scores_gemma":[0.0007273295,0.00625522,0.316925,0.0004477845,0.0004765314,0.002506994,0.005290905,0.6197029,0.01610013,0.01170179,0.0196627,0.0002027336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827951,0.001153726,0.01088174,0.0007636989,0.00003535839,0.0001970542,0.0008159673,0.0004790943,0.00287835],"genre_scores_gemma":[0.9838213,0.0002816168,0.01330199,0.00007630926,0.00002736199,0.0001134574,0.001699397,0.0001290732,0.0005495842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0278858,"threshold_uncertainty_score":0.147476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1229223089832377,"score_gpt":0.4284261846884259,"score_spread":0.3055038757051882,"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."}}