{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01366654,0.0003253698,0.0005442456,0.00483484,0.001710578,0.003236042,0.0008765295,0.001054953,0.001758842],"category_scores_gemma":[0.1471189,0.0005533031,0.0005828787,0.003784073,0.002364682,0.009539221,0.004887024,0.002187759,0.0006032133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073389,"about_ca_system_score_gemma":0.003994755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004553612,"about_ca_topic_score_gemma":0.005488683,"domain_scores_codex":[0.9897541,0.003486992,0.001093499,0.00180709,0.003262787,0.0005953431],"domain_scores_gemma":[0.8834149,0.05284267,0.01701486,0.02336885,0.02130892,0.002049863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008306609,0.000186664,0.6576696,0.0005456737,0.0002342178,0.0005899842,0.01113099,0.009290393,0.01669142,0.1131998,0.003402593,0.1862281],"study_design_scores_gemma":[0.0001973177,0.0006640716,0.2869127,0.000862926,0.0004738396,0.002018934,0.009961264,0.2209289,0.07626119,0.3567618,0.04457791,0.0003790948],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.66259,0.0004520457,0.3232294,0.0006289611,0.000171986,0.0001998583,0.002037093,0.001157994,0.009532563],"genre_scores_gemma":[0.9309652,0.0001514594,0.06631658,0.00006989756,0.0000450957,0.0000984898,0.001039023,0.0002521086,0.001062152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01366654,"threshold_uncertainty_score":0.07227641,"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."}}