{"id":"W2165739648","doi":"10.1109/icpc.2008.41","title":"NICAD: Accurate Detection of Near-Miss Intentional Clones Using Flexible Pretty-Printing and Code Normalization","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":519,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Parsing; Normalization (sociology); Agile software development; Programming language; Precision and recall; Transformation (genetics); Source code; Disk formatting; Code generation; Rule-based machine translation; Compiler; Code (set theory); Artificial intelligence; Natural language processing; Software engineering; 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":[0.0002351163,0.00006842682,0.00008547276,0.0001032326,0.0001459767,0.00006152417,0.0002093176,0.00004093793,0.000008233827],"category_scores_gemma":[0.0003521015,0.00006771601,0.00002403556,0.0003990736,0.00005972873,0.0005105855,0.0002209949,0.00008610725,0.000003181754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002850665,"about_ca_system_score_gemma":0.00005041818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007199284,"about_ca_topic_score_gemma":0.00000580246,"domain_scores_codex":[0.9991986,0.0000272713,0.0001819997,0.0001934629,0.0002410618,0.0001576142],"domain_scores_gemma":[0.999384,0.0001575644,0.00005572764,0.0001837812,0.0001708079,0.00004806789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000530678,0.0001608406,0.3947738,0.0003570957,0.0001024658,0.00002416681,0.002096783,0.145448,0.4092188,0.01162524,0.00009366904,0.03604604],"study_design_scores_gemma":[0.0001503938,0.00002924936,0.1076363,0.0000233427,0.000001872423,0.00008760639,0.000008245008,0.7870974,0.1046754,0.0001091684,0.00009419821,0.00008679045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4690014,0.00003019637,0.5307119,0.00001958062,0.00006262719,0.00004583492,3.444597e-7,0.00009855458,0.00002949983],"genre_scores_gemma":[0.9376103,0.00001476434,0.0622311,0.000009419958,0.00001908166,0.000002938147,7.466028e-7,0.000006436282,0.0001052222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6416494,"threshold_uncertainty_score":0.2761379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0470208530369328,"score_gpt":0.2932180374607296,"score_spread":0.2461971844237968,"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."}}