{"id":"W4206541176","doi":"10.1109/tdsc.2021.3138700","title":"Dataset Characteristics for Reliable Code Authorship Attribution","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Attribution; Computer science; Coding (social sciences); Source code; Field (mathematics); Robustness (evolution); Code (set theory); Data science; Data mining; Benchmark (surveying); Information retrieval; Set (abstract data type); Artificial intelligence; Programming language","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":[0.0005016448,0.0001587135,0.0002018056,0.0001061079,0.0004495671,0.0002809649,0.0003051691,0.0001165337,0.00001369718],"category_scores_gemma":[0.00007714914,0.0001729316,0.00005659695,0.000388454,0.00002173741,0.0002599323,0.00001311478,0.0003696379,0.00001688063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000596917,"about_ca_system_score_gemma":0.0001153167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001184978,"about_ca_topic_score_gemma":0.00001107881,"domain_scores_codex":[0.9985453,0.00005158126,0.0002387759,0.000502416,0.0002377811,0.0004241211],"domain_scores_gemma":[0.9984186,0.000753029,0.00004873564,0.0004532676,0.0001736855,0.000152682],"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":[0.0003715925,0.002215724,0.00325677,0.002857414,0.0008738734,0.001202659,0.005087922,0.1949577,0.0247669,0.02752402,0.03659662,0.7002888],"study_design_scores_gemma":[0.0009668092,0.0002034208,0.0009783738,0.000181457,0.00003734451,0.0002507777,0.00003110688,0.8997346,0.05496499,0.0005665835,0.04156107,0.0005235024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02467693,0.0001009059,0.9730092,0.0003843313,0.0007775659,0.0001685482,0.0006863444,0.0001898311,0.000006348516],"genre_scores_gemma":[0.9531696,0.00003320948,0.04614782,0.0001304557,0.00008422831,0.0000154985,0.0002254402,0.00001983487,0.0001739526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9284926,"threshold_uncertainty_score":0.7051948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607006238654237,"score_gpt":0.2916618682774196,"score_spread":0.2555918058908772,"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."}}