{"id":"W4221058968","doi":"10.32604/iasc.2022.027349","title":"Improve Representation for Cross-Language Clone Detection by Pretrain Using Tree Autoencoder","year":2022,"lang":"en","type":"article","venue":"Intelligent Automation & Soft Computing","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Autoencoder; Artificial intelligence; Deep learning; Tree (set theory); Context (archaeology); Node (physics); Encoder; Embedding; Feature learning; Pattern recognition (psychology); Machine learning","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":[0.001239279,0.0001981572,0.0001904461,0.000298295,0.0007076634,0.0004265777,0.0007360355,0.00006596433,0.00002855733],"category_scores_gemma":[0.001038877,0.000239315,0.0001294965,0.0008473058,0.00003461336,0.0005153204,0.0004917331,0.0003126637,0.00001002367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006065334,"about_ca_system_score_gemma":0.00008427822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008538743,"about_ca_topic_score_gemma":0.000003094892,"domain_scores_codex":[0.9974705,0.0001581099,0.0005505126,0.0006401521,0.0007054164,0.0004753358],"domain_scores_gemma":[0.9977767,0.001178716,0.0002619479,0.0004974936,0.0001951927,0.00008990322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002150105,0.0001032598,0.001584764,0.00007571816,0.00004831816,0.000006129313,0.00578418,0.462348,0.1122459,0.0002349921,0.0003631288,0.4171841],"study_design_scores_gemma":[0.000279287,0.0001174061,0.001244164,0.00001136648,0.000005787429,0.00002415284,0.0001701614,0.9201878,0.07716908,0.0002031336,0.0003652206,0.0002224339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2785271,0.0001107065,0.71863,0.00005657255,0.001153057,0.0005708798,0.00001337734,0.0009251119,0.00001325676],"genre_scores_gemma":[0.9195457,6.650805e-7,0.07991396,0.00006270141,0.000173565,0.00009052643,0.00003787816,0.00003600091,0.0001389795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6410186,"threshold_uncertainty_score":0.9758981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02670070496416517,"score_gpt":0.3361846129183926,"score_spread":0.3094839079542274,"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."}}