{"id":"W4288406204","doi":"10.48550/arxiv.1903.11242","title":"An Empirical Study on Practicality of Specification Mining Algorithms on\\n a Real-world Application","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Debugging; Computer science; Program comprehension; Context (archaeology); Implementation; Inference; Programming language; Abstraction; Software engineering; Set (abstract data type); Root cause; Software; Algorithm; Artificial intelligence; Software system; Reliability engineering","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"],"consensus_categories":[],"category_scores_codex":[0.002281069,0.000644682,0.0008359576,0.0008423784,0.0003175988,0.0001882393,0.002698731,0.0004100985,0.00001505105],"category_scores_gemma":[0.0004117945,0.0007512539,0.0002555595,0.00202737,0.0002498758,0.0004928683,0.001035907,0.001141104,0.0001314807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006619652,"about_ca_system_score_gemma":0.0004315976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008575229,"about_ca_topic_score_gemma":0.00004110177,"domain_scores_codex":[0.9939219,0.001155945,0.0008039751,0.003079169,0.0004706979,0.000568263],"domain_scores_gemma":[0.9903374,0.002066844,0.001502493,0.005101031,0.0006725579,0.0003196824],"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":[0.0009122141,0.0160182,0.7830014,0.0002296706,0.0003154416,0.0002097941,0.006104938,0.1118079,0.00007366513,0.05292884,0.001441367,0.02695662],"study_design_scores_gemma":[0.0006537738,0.00228953,0.221637,0.0002624101,0.0001587061,0.000002997337,0.0003193982,0.7547541,0.0002160535,0.01881482,0.000135328,0.0007559138],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3943536,0.000002309373,0.5993369,0.000118559,0.0003048133,0.001329774,0.00001423066,0.001918568,0.002621276],"genre_scores_gemma":[0.9809891,0.00003419727,0.01831682,0.0001099,0.0001526391,0.000009490489,0.00002945745,0.00004434998,0.0003140685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6429462,"threshold_uncertainty_score":0.9994938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2026427942074081,"score_gpt":0.3137623839398878,"score_spread":0.1111195897324797,"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."}}