{"id":"W2901368228","doi":"10.1109/scam.2018.00023","title":"[Research Paper] CroLSim: Cross Language Software Similarity Detector Using API Documentation","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Documentation; Software documentation; Python (programming language); Java; Application programming interface; Source code; Software; Programming language; Software engineering; World Wide Web; Software development; Software construction","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":[0.001443251,0.0001526895,0.0001342371,0.0002718802,0.0004445603,0.0009662662,0.001250559,0.0001132232,0.0006446118],"category_scores_gemma":[0.001435441,0.0001432278,0.0000525158,0.00115621,0.0002322631,0.001314009,0.0007587646,0.0003952144,0.0004505337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002370637,"about_ca_system_score_gemma":0.0001637451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000829303,"about_ca_topic_score_gemma":0.00009975047,"domain_scores_codex":[0.9972458,0.0001600334,0.0002144347,0.0005596773,0.001048757,0.0007712984],"domain_scores_gemma":[0.9973286,0.0009967657,0.0000289888,0.0008990315,0.0005472616,0.0001993889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000192802,0.0007452058,0.3195959,0.0006534159,0.0003037407,0.0007117165,0.02361797,0.004530998,0.3479685,0.01076185,0.01346764,0.2774502],"study_design_scores_gemma":[0.002445689,0.0008934024,0.3121268,0.0001355878,0.00001146823,0.0001231575,0.0005110066,0.2253349,0.447459,0.00405925,0.005349029,0.001550614],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4879818,0.00006028754,0.5107005,0.00008317392,0.0002481384,0.000183338,0.000002521661,0.0005217777,0.0002185189],"genre_scores_gemma":[0.8607343,0.000002379214,0.1380812,0.0001383779,0.0002877153,0.00001878508,0.000002256117,0.00002346578,0.000711538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3727525,"threshold_uncertainty_score":0.9317727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04907147549712693,"score_gpt":0.4025824023901418,"score_spread":0.3535109268930149,"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."}}