{"id":"W4415991171","doi":"10.1007/s10664-025-10732-z","title":"MonoEmbed: Enhancing LLM representations for monolith to microservices decomposition through contrastive learning","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microservices; Flexibility (engineering); Representation (politics); Decomposition; Adaptation (eye); Rank (graph theory); Benchmark (surveying)","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":[0.000253632,0.0001920255,0.0002753912,0.0001358776,0.0002314019,0.0001593915,0.0004349218,0.000105538,0.000003194504],"category_scores_gemma":[0.0005965588,0.0001919842,0.0001191457,0.0007213475,0.00001212209,0.000523696,0.0001969553,0.0001986269,0.00001939588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000174507,"about_ca_system_score_gemma":0.00007107793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006588205,"about_ca_topic_score_gemma":0.0000155557,"domain_scores_codex":[0.9984955,0.0000342404,0.0003853131,0.0005262367,0.0001557507,0.0004029741],"domain_scores_gemma":[0.9984205,0.000909233,0.00006072532,0.0003492554,0.0001621228,0.00009814694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001007637,0.0003181121,0.2124525,0.001052424,0.0003027043,0.00001486368,0.01462541,0.737619,0.008281263,0.001973957,0.003774544,0.01948436],"study_design_scores_gemma":[0.002663786,0.0007182948,0.4574548,0.001452285,0.000104805,0.00002678263,0.0005640723,0.3971105,0.0736329,0.003198813,0.06124411,0.001828825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2351282,0.0001511644,0.7626957,0.0004271052,0.0005286993,0.0004204834,0.000004278265,0.0006206096,0.00002372287],"genre_scores_gemma":[0.7671522,0.000005460251,0.2318572,0.0004956452,0.000105585,0.0002662383,0.00001124757,0.00001555434,0.00009075827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5320241,"threshold_uncertainty_score":0.7828889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01145571992058817,"score_gpt":0.3275772368153418,"score_spread":0.3161215168947537,"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."}}