{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006112858,0.0002242909,0.000265294,0.0003689325,0.000186867,0.0002999126,0.0007422165,0.00006750785,0.00005635538],"category_scores_gemma":[0.001329896,0.0002581751,0.00005440255,0.00119923,0.00002230362,0.0007628214,0.001192246,0.001040572,0.00001205264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002365483,"about_ca_system_score_gemma":0.00003775596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002969155,"about_ca_topic_score_gemma":0.000008961553,"domain_scores_codex":[0.9978762,0.00009268586,0.0002715288,0.0005646623,0.0005716567,0.0006232198],"domain_scores_gemma":[0.9978053,0.001563169,0.00003242763,0.000368035,0.00003347424,0.0001975723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007747304,0.0000667416,0.5060139,0.0001026968,0.00002288428,0.0002816231,0.001760354,0.4648966,0.00009256024,0.0002261965,0.0006413293,0.02588733],"study_design_scores_gemma":[0.0009644614,0.0002959033,0.387359,0.0001204962,0.000005856989,0.0002450873,0.0002077878,0.4498214,0.0001146555,0.0002219432,0.1596311,0.001012235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2989624,0.006352085,0.6917799,0.0007732956,0.0006305519,0.0001855193,0.000001337389,0.001309147,0.000005771686],"genre_scores_gemma":[0.9516197,0.0002547941,0.04732112,0.000265793,0.0001050718,0.000208008,0.000005694144,0.00007752782,0.0001422835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6526573,"threshold_uncertainty_score":0.9999871,"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."}}