{"id":"W4403413357","doi":"10.1145/3674805.3686695","title":"A Transformer-based Approach for Augmenting Software Engineering Chatbots Datasets","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Calgary","funders":"","keywords":"Computer science; Transformer; Software; Software engineering; Programming language; Engineering; Electrical 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":[],"consensus_categories":[],"category_scores_codex":[0.0002391761,0.0001092423,0.0000930504,0.0000971846,0.00005394782,0.0002431084,0.0004181383,0.00003734094,0.000007580094],"category_scores_gemma":[0.00002567365,0.00009702774,0.00006768449,0.0001761318,0.0000044702,0.0003910801,0.00003432463,0.00007598336,0.000005941599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002709559,"about_ca_system_score_gemma":0.00005273946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007622877,"about_ca_topic_score_gemma":8.632658e-7,"domain_scores_codex":[0.9990394,0.000004950403,0.0001546179,0.0003870943,0.0001434258,0.000270518],"domain_scores_gemma":[0.9995143,0.00009411782,0.000009633734,0.0003130161,0.00001232418,0.0000566545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007932431,0.0001375863,0.00009473658,0.002998577,0.0001278005,0.00003297138,0.00129301,0.3332304,0.004154854,0.1919474,0.004282997,0.4616916],"study_design_scores_gemma":[0.0001329458,0.00001367466,0.000003828667,0.00003643646,0.00000562367,0.000003873737,0.000005098973,0.988158,0.002388215,0.00009244383,0.009032415,0.0001274064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002673624,0.0001870986,0.9978887,0.0002010589,0.0002553102,0.0002454686,0.00002933404,0.0007510399,0.0001746472],"genre_scores_gemma":[0.1505975,8.847836e-7,0.848954,0.0001238587,0.00007294401,0.00007596238,0.00007257437,0.00001313509,0.0000890872],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6549276,"threshold_uncertainty_score":0.3956676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249697164770974,"score_gpt":0.2452655686757533,"score_spread":0.2202958521986559,"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."}}