{"id":"W1794751911","doi":"","title":"Deriving high-level abstractions from legacy software using example-driven clustering","year":2011,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Cluster analysis; Program comprehension; Software maintenance; Graph; Programming language; Theoretical computer science; Software; Software system; Software engineering; Data mining; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002348558,0.00103687,0.0006447198,0.001768864,0.0009791479,0.001690995,0.002422809,0.001170181,0.002323478],"category_scores_gemma":[0.0107584,0.0009419408,0.002044487,0.001327688,0.001960303,0.002354188,0.002867362,0.001779817,0.0006353711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038798,"about_ca_system_score_gemma":0.001797712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002445625,"about_ca_topic_score_gemma":0.004881056,"domain_scores_codex":[0.9980298,0.0005993142,0.0001359158,0.0003095166,0.0008050799,0.0001204225],"domain_scores_gemma":[0.9947551,0.002718653,0.0004443564,0.001252111,0.0007071162,0.0001226174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009331272,0.0001293043,0.003358104,0.0007535807,0.0001242765,0.0006452981,0.002109114,0.6446754,0.01940044,0.1536789,0.002648274,0.1723839],"study_design_scores_gemma":[0.00002994604,0.00006068364,0.0004899072,0.0000808473,0.00004812191,0.0002278282,0.000287855,0.8739787,0.01118437,0.1043308,0.009251444,0.00002951136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0101799,0.00002824275,0.9883917,0.00006766896,0.000005295513,0.00009163201,0.00006040907,0.0004276518,0.0007475382],"genre_scores_gemma":[0.05800641,0.00008879942,0.9406438,0.00002129995,0.00000573479,0.0001083829,0.0003432856,0.0002270016,0.0005552464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002445625,"threshold_uncertainty_score":0.01242054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3262199322302999,"score_gpt":0.3984240914621571,"score_spread":0.07220415923185719,"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."}}