{"id":"W4294627637","doi":"10.1002/smr.2503","title":"From legacy to microservices: A type‐based approach for microservices identification using machine learning and semantic analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McMaster University; Mila - Quebec Artificial Intelligence Institute; Concordia University; École de Technologie Supérieure","funders":"","keywords":"Microservices; Computer science; Architectural style; Software engineering; Identification (biology); Scalability; Legacy system; Artificial intelligence; Cloud computing; Machine learning; Programming language; Architecture; Software; Database; 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":[],"consensus_categories":[],"category_scores_codex":[0.0009156007,0.0001216399,0.000288771,0.0003645513,0.0005538881,0.0002501202,0.0003488103,0.00004401774,0.000007072963],"category_scores_gemma":[0.00007943844,0.0001064176,0.00008667109,0.001174681,0.00002137404,0.0006763821,0.0001195394,0.0001815059,3.750574e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009300807,"about_ca_system_score_gemma":0.0001384293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002220144,"about_ca_topic_score_gemma":0.00001487331,"domain_scores_codex":[0.9987019,0.0001029995,0.0004493055,0.000297547,0.0002930765,0.0001551165],"domain_scores_gemma":[0.9986759,0.0001134328,0.0005010589,0.0001509877,0.0004613897,0.00009722279],"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":[0.0005034947,0.0003463816,0.802712,0.001752553,0.000551188,0.000004682312,0.01019324,0.1664529,0.009908896,0.00002644131,0.00004392821,0.00750427],"study_design_scores_gemma":[0.001032543,0.0003147985,0.03398253,0.00007297879,0.0004119525,0.0000681731,0.001831461,0.9600886,0.0006460107,0.0005028794,0.000739605,0.000308497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4824584,0.001464684,0.5157243,0.00008722984,0.0001155322,0.0001155495,0.00001024891,0.00002359537,4.58533e-7],"genre_scores_gemma":[0.9342347,0.00001129343,0.0655129,0.0001209892,0.00006745423,0.0000112209,0.00002047907,0.000007749183,0.000013214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7936357,"threshold_uncertainty_score":0.4339584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01570769090064231,"score_gpt":0.2828532947039066,"score_spread":0.2671456038032642,"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."}}