{"id":"W4378474030","doi":"10.1007/s10664-023-10317-8","title":"Using the uniqueness of global identifiers to determine the provenance of Python software source code","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Identifier; Python (programming language); Computer science; Source code; Software; Open source; Source lines of code; Database; Programming language; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009006191,0.0002642915,0.0003481295,0.0001405384,0.0001338719,0.00008707017,0.002082092,0.0001073892,0.000003434426],"category_scores_gemma":[0.005694861,0.0001849307,0.0001607844,0.003591679,0.0000979251,0.0002149689,0.001018553,0.0003082205,0.000012732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001939113,"about_ca_system_score_gemma":0.0001548397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006861271,"about_ca_topic_score_gemma":0.000006025543,"domain_scores_codex":[0.9975078,0.00007831123,0.0004857901,0.0004555294,0.0008175889,0.000654984],"domain_scores_gemma":[0.9960653,0.002310962,0.0001121727,0.001132716,0.0002125447,0.0001663598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00001756379,0.00003658905,0.1754474,0.0003003596,0.00007045102,0.00003204285,0.001195222,0.8098626,0.00205971,0.0002416562,0.001025873,0.009710601],"study_design_scores_gemma":[0.0007027884,0.0003238485,0.5595908,0.000849369,0.00005349954,0.0001256068,0.0001236709,0.4031289,0.02364308,0.000659194,0.009665016,0.001134317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.391875,0.0001023696,0.606535,0.0002761974,0.0003263956,0.0002706682,0.00001403242,0.0005993103,0.000001087936],"genre_scores_gemma":[0.934025,0.000005732264,0.06561042,0.00008984856,0.0000922676,0.00006086044,0.00000230321,0.00005201456,0.00006151231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.54215,"threshold_uncertainty_score":0.7541254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05727007110122434,"score_gpt":0.3327735716719666,"score_spread":0.2755035005707423,"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."}}