{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001657256,0.0002773112,0.0004104999,0.0003337589,0.0000684316,0.00015501,0.001330472,0.0001823171,0.000004176152],"category_scores_gemma":[0.0003258334,0.0002446701,0.0000803318,0.0004090614,0.00003731866,0.0001381599,0.0005511274,0.0005390074,0.00003691077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634326,"about_ca_system_score_gemma":0.0001516191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000576819,"about_ca_topic_score_gemma":0.00001652836,"domain_scores_codex":[0.9969396,0.0003657252,0.0005705396,0.00121998,0.0006777956,0.0002263323],"domain_scores_gemma":[0.9946854,0.001127661,0.0005685918,0.003280599,0.0002426798,0.00009509183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002100379,0.01723364,0.5367213,0.0002640368,0.0001632029,0.00002041603,0.008676137,0.002816312,0.0001937397,0.03006212,0.02834009,0.3752989],"study_design_scores_gemma":[0.0003503941,0.002219443,0.5607446,0.0002404508,0.00004005024,0.000003179276,0.0001013557,0.4001001,0.001527214,0.03359029,0.0003491845,0.0007336846],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05649105,0.000002362873,0.926365,0.0007008836,0.0002442872,0.001292305,0.000004662823,0.006369927,0.008529563],"genre_scores_gemma":[0.730559,0.000002185239,0.2689442,0.0001568529,0.00009186775,0.0001329673,0.00001903155,0.00001636062,0.00007755881],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6740679,"threshold_uncertainty_score":0.9977355,"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."}}