{"id":"W2167809408","doi":"10.1109/wcre.1999.806964","title":"Experiments with clustering as a software remodularization method","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":311,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cluster analysis; Computer science; Reverse engineering; Data mining; Domain (mathematical analysis); Software; Code (set theory); Source code; Software engineering; Theoretical computer science; Machine learning; Programming language; Mathematics","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":[0.0002955637,0.0001005411,0.00008685096,0.0001030363,0.00006597255,0.0001365293,0.0003752902,0.00003757535,0.00005153942],"category_scores_gemma":[0.0005169641,0.00008314168,0.00001814455,0.0004542589,0.000009455002,0.0003371588,0.0001103459,0.00008685204,0.00006073934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005594319,"about_ca_system_score_gemma":0.00006658874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002502757,"about_ca_topic_score_gemma":0.000001737413,"domain_scores_codex":[0.9989181,0.00006878415,0.00009415582,0.0003185838,0.0003485029,0.0002519314],"domain_scores_gemma":[0.9991204,0.0002033775,0.00001867659,0.0004920353,0.00007194216,0.00009356584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009875432,0.0007917543,0.105217,0.0003464909,0.0004631484,0.0009891425,0.01205755,0.1633535,0.04269819,0.3544243,0.002501864,0.3170583],"study_design_scores_gemma":[0.003665315,0.001044999,0.01374581,0.0002028982,0.00001520776,0.001289426,0.000228505,0.428956,0.5241222,0.005922048,0.01883243,0.001975137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004240517,0.00003039389,0.993438,0.00004599551,0.0001044868,0.0001303702,8.224077e-8,0.0005285055,0.001481645],"genre_scores_gemma":[0.1586393,9.498107e-7,0.8401676,0.00009035248,0.00000865828,0.00001985921,5.661903e-7,0.00001376451,0.001058964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4814241,"threshold_uncertainty_score":0.3390419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02114513403742583,"score_gpt":0.3051099445116784,"score_spread":0.2839648104742525,"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."}}