{"id":"W2954741184","doi":"10.1109/msr.2019.00080","title":"Predicting Co-Changes between Functionality Specifications and Source Code in Behavior Driven Development","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Traceability; Feature (linguistics); Source code; Documentation; Codebase; Programming language; Feature model; Software; Software development; Software engineering; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0003106789,0.00006725733,0.00008451341,0.0001212501,0.00005172534,0.000065096,0.0002699463,0.00003656925,0.00004135651],"category_scores_gemma":[0.0000651498,0.00006643728,0.000008258924,0.0002053074,0.00001730094,0.0001260275,0.0001699391,0.0001220893,0.00007610075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009057583,"about_ca_system_score_gemma":0.00005630886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003184602,"about_ca_topic_score_gemma":0.00006398003,"domain_scores_codex":[0.9991459,0.00002191495,0.0001245263,0.0002713065,0.0002548023,0.0001816091],"domain_scores_gemma":[0.9991928,0.000428823,0.00002045318,0.0002517562,0.00003787629,0.00006824655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[3.432809e-7,0.00001383777,0.9904397,0.000006768138,0.000003609539,5.898687e-7,0.0003939939,0.00007241295,0.0001638217,0.0002696121,0.00004177074,0.008593588],"study_design_scores_gemma":[0.0001260604,0.00001373328,0.9935166,0.000009750985,9.377271e-7,0.000001908943,0.00003081115,0.00203064,0.000765838,0.00001336785,0.003412835,0.0000775681],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8519208,0.00001370158,0.1471926,0.0002381667,0.00005328194,0.0001937349,0.00000223673,0.000165633,0.0002199034],"genre_scores_gemma":[0.9744907,0.000001831844,0.02452142,0.00001463766,0.00003102288,0.00004541464,0.000006920591,0.000006026268,0.0008820491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1226711,"threshold_uncertainty_score":0.2709233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0741375878839423,"score_gpt":0.2966963779232075,"score_spread":0.2225587900392652,"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."}}