{"id":"W2120293505","doi":"10.1109/iceccs.2011.36","title":"Analyzing and Forecasting Near-Miss Clones in Evolving Software: An Empirical Study","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Software evolution; Computer science; clone (Java method); Software maintenance; Programming language; Java; Software system; Dependency (UML); Software development; Software; Code (set theory); Software engineering; Software construction; Biology","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":[0.0009258842,0.000127575,0.0001731423,0.0002042127,0.0001121034,0.0002451049,0.0005728005,0.0000448273,0.00002270183],"category_scores_gemma":[0.001241666,0.000115727,0.00002054833,0.0006655108,0.00003355493,0.0007789375,0.0004861639,0.0002168647,0.000006343227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004065729,"about_ca_system_score_gemma":0.00004415965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005513619,"about_ca_topic_score_gemma":0.0001564055,"domain_scores_codex":[0.9985569,0.00008982467,0.0002353361,0.0004717331,0.0002557633,0.0003904013],"domain_scores_gemma":[0.9987193,0.0005862201,0.00002738687,0.0004429154,0.00006280298,0.0001613135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002882936,0.0001087303,0.9754984,0.000007858456,0.000006229833,0.00006372997,0.00391102,0.00009215644,0.00001357927,0.0000282827,0.00001459281,0.02025258],"study_design_scores_gemma":[0.0002332998,0.0001757591,0.8401023,0.00001156611,0.000001462071,0.00001422705,0.000146581,0.1589438,0.00004967433,0.000174946,0.000005042356,0.0001413887],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7312509,0.00006357012,0.2681389,0.00001889189,0.00005767558,0.0001322912,8.905833e-8,0.0002760615,0.00006162658],"genre_scores_gemma":[0.7895244,8.513011e-7,0.210394,0.00001449295,0.00001751715,0.00001141099,1.709971e-7,0.00001085389,0.00002633036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1588516,"threshold_uncertainty_score":0.4719209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08643892818750509,"score_gpt":0.3187676826238661,"score_spread":0.232328754436361,"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."}}