{"id":"W3151667270","doi":"10.1109/asonam49781.2020.9381381","title":"Identifying Social Networks of Programmers using Text Mining for Code Similarity Detection","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Code (set theory); Source code; Similarity (geometry); Plagiarism detection; Data mining; Information retrieval; Programming language; Artificial intelligence; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008563114,0.0007771612,0.0004862186,0.01056237,0.0007034685,0.0009304149,0.0007349201,0.0007391784,0.001001839],"category_scores_gemma":[0.004380092,0.0001948529,0.000676889,0.004579597,0.0002956694,0.001535395,0.0009433905,0.0004618871,0.0007641616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000422373,"about_ca_system_score_gemma":0.0005547038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002592032,"about_ca_topic_score_gemma":0.004942542,"domain_scores_codex":[0.9986151,0.0002910766,0.0001516733,0.0004516316,0.0003885443,0.0001019112],"domain_scores_gemma":[0.9963909,0.001794433,0.0007793981,0.0003350306,0.0005007458,0.0001994758],"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":[0.0007321335,0.00125715,0.2655262,0.001199532,0.000402746,0.001519237,0.002167203,0.01364372,0.04107308,0.005107436,0.01556575,0.6518059],"study_design_scores_gemma":[0.00008426191,0.0005840737,0.2698813,0.0001589529,0.0002373558,0.002372608,0.003515982,0.652972,0.02847192,0.01487329,0.02672669,0.0001215624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8276722,0.0009702603,0.1481267,0.0005738918,0.000119232,0.0009286728,0.01330045,0.002068628,0.006240115],"genre_scores_gemma":[0.8501198,0.0004388702,0.1303725,0.00007257151,0.0001310125,0.0007566364,0.01509153,0.00006909894,0.002947898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01056237,"threshold_uncertainty_score":0.005153894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1169008893077905,"score_gpt":0.3397640610776878,"score_spread":0.2228631717698973,"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."}}