{"id":"W2153183909","doi":"10.1109/csmr.2000.827321","title":"Architectural design recovery using data mining techniques","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Matching (statistics); Data mining; Process (computing); Legacy system; Information retrieval; Query language; Software; Database; Programming language; Artificial intelligence","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":[0.0005021378,0.0001168051,0.0001268415,0.0001041515,0.00006316142,0.00007872776,0.001494913,0.00004145411,0.00001429612],"category_scores_gemma":[0.0008494843,0.0001020154,0.00002022278,0.0002504025,0.00002791638,0.0007956359,0.000789678,0.0001037148,0.000007157556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000031137,"about_ca_system_score_gemma":0.000009721273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005859759,"about_ca_topic_score_gemma":5.206094e-7,"domain_scores_codex":[0.9989943,0.0001153019,0.0001423808,0.000377241,0.0001256601,0.0002450961],"domain_scores_gemma":[0.9977872,0.0009729304,0.00004079812,0.001141108,0.00001932462,0.00003857737],"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":[0.000001485914,0.000007968871,0.00001296142,0.000006214845,0.000008906799,0.0000176547,0.0001761296,0.05504854,0.003490243,0.0002517825,0.0007748762,0.9402032],"study_design_scores_gemma":[0.00006394424,0.00007592799,0.00003821695,0.00003447246,0.000004277126,0.0001765073,0.00001359996,0.9655858,0.025877,0.007040495,0.0007438912,0.0003459218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005741445,0.0001749409,0.9969903,0.0000948765,0.0002027901,0.00008775833,9.732121e-7,0.001595272,0.0002789425],"genre_scores_gemma":[0.004008662,0.00001338967,0.9956273,0.0001080419,0.00005025343,0.000003151965,6.992942e-7,0.00001079051,0.0001776455],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9398573,"threshold_uncertainty_score":0.4160065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3713034259489712,"score_gpt":0.3471063374343569,"score_spread":0.02419708851461427,"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."}}