{"id":"W3185295980","doi":"10.1007/s10664-021-10099-x","title":"Clones in deep learning code: what, where, and why?","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Timeline; Source lines of code; Context (archaeology); Python (programming language); Dependability; Software development; Java; Software evolution; Software system; Software engineering; Machine learning; Software quality; Code (set theory); Software; Programming language; Software construction; Biology","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":[0.00626194,0.0003959183,0.0005534513,0.001396865,0.001075719,0.002350294,0.001117415,0.002233875,0.002451752],"category_scores_gemma":[0.1298013,0.0005521412,0.0004591212,0.001920214,0.005527134,0.0105916,0.002326772,0.003185174,0.000383291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002328058,"about_ca_system_score_gemma":0.002130243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00638975,"about_ca_topic_score_gemma":0.009067275,"domain_scores_codex":[0.9934296,0.002333936,0.0003049168,0.001122242,0.002283872,0.0005254023],"domain_scores_gemma":[0.8946272,0.072832,0.01001798,0.01202131,0.008804229,0.00169731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004218371,0.000358155,0.5429724,0.0003404673,0.0001970598,0.0005441908,0.007558555,0.02203102,0.00458657,0.09009612,0.00666101,0.3242327],"study_design_scores_gemma":[0.0001375919,0.0005590032,0.1911257,0.0008802263,0.0003808433,0.002073974,0.009096364,0.2704273,0.01951661,0.493253,0.01237959,0.000169735],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9512247,0.001338504,0.0398411,0.003681263,0.0000654203,0.00002888108,0.0001635042,0.0003416952,0.003315028],"genre_scores_gemma":[0.9914062,0.0002295909,0.006951903,0.00022585,0.00003077748,0.00001739851,0.0001077383,0.0001106739,0.0009199992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00638975,"threshold_uncertainty_score":0.0331167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01744720412160194,"score_gpt":0.2649686041091264,"score_spread":0.2475213999875244,"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."}}