{"id":"W4413268009","doi":"10.1145/3696630.3731666","title":"Get on the Train or be Left on the Station: Using LLMs for Software Engineering Research","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Software; Computer science; Engineering management; Engineering; Operating system","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002603614,0.0001391588,0.0001101661,0.0002794825,0.0004300077,0.0003834821,0.001435756,0.0000588501,0.00006820652],"category_scores_gemma":[0.008485671,0.00007313609,0.0000585585,0.0009186583,0.00005478792,0.0001331293,0.0002557347,0.0004760571,0.00001647149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001733316,"about_ca_system_score_gemma":0.0002617357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002935593,"about_ca_topic_score_gemma":0.0000123442,"domain_scores_codex":[0.9980972,0.0001205002,0.0001672632,0.0003641224,0.0007098796,0.0005409895],"domain_scores_gemma":[0.9783789,0.0204904,0.00001537942,0.0008455559,0.0002130669,0.00005669018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009970108,0.0001366264,0.0005133238,0.0002011775,0.0001321575,0.00002352065,0.002995888,0.1009002,0.001472939,0.7942856,0.07774121,0.02149764],"study_design_scores_gemma":[0.000475318,0.0003909022,0.003067634,0.0002792376,0.00000476126,0.000007134737,0.0003516855,0.9413387,0.01364966,0.003073992,0.03705014,0.0003108027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03790549,0.00002564873,0.9454983,0.01485519,0.0003090647,0.0008468512,0.000008657682,0.0003400219,0.0002107033],"genre_scores_gemma":[0.8206319,0.00001154459,0.1653078,0.002777705,0.0002729064,0.0004147914,0.000005691624,0.00007065362,0.01050705],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8404385,"threshold_uncertainty_score":0.9998662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1492130351029197,"score_gpt":0.3841645751861282,"score_spread":0.2349515400832085,"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."}}