{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02174286,0.001023668,0.0008972662,0.005259944,0.001911995,0.00442793,0.002082475,0.002235132,0.002071321],"category_scores_gemma":[0.1610919,0.0002579444,0.001133152,0.006625595,0.001192492,0.003644193,0.002453392,0.001924695,0.001543546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514069,"about_ca_system_score_gemma":0.002771867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001850938,"about_ca_topic_score_gemma":0.00226135,"domain_scores_codex":[0.971417,0.00794027,0.006367421,0.004792903,0.008388028,0.001094488],"domain_scores_gemma":[0.8593683,0.0663571,0.01093571,0.03488844,0.0266184,0.001832104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002259444,0.001639789,0.4370867,0.003381805,0.0006713906,0.0009214769,0.002251027,0.02467959,0.02238876,0.01743121,0.1422293,0.3450596],"study_design_scores_gemma":[0.0008216418,0.001258308,0.4223519,0.001644783,0.0006689233,0.003203665,0.004394999,0.1764502,0.06071302,0.05346765,0.274552,0.0004729857],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6087066,0.002893197,0.1550907,0.00595029,0.001501392,0.004078252,0.1998124,0.007211444,0.0147557],"genre_scores_gemma":[0.6287972,0.0004459471,0.1470124,0.0005116315,0.0003250233,0.004613325,0.2164765,0.0005835692,0.001234369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02174286,"threshold_uncertainty_score":0.1149886,"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."}}