{"id":"W3216616474","doi":"10.18280/isi.260504","title":"Reusable Component Retrieval from a Large Repository Using Word2Vec with Continuous Bag of Words","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Word2vec; Component (thermodynamics); Computer science; Word embedding; Word (group theory); Code (set theory); Process (computing); Representation (politics); Embedding; Artificial intelligence; Information retrieval; Natural language processing; Data mining; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004124703,0.002333768,0.001001252,0.003018856,0.0005047,0.000882455,0.0009866257,0.0007603807,0.002866981],"category_scores_gemma":[0.001637311,0.0004453871,0.001396192,0.003275606,0.0003871422,0.001921574,0.001180995,0.001044082,0.002983132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005430412,"about_ca_system_score_gemma":0.001237645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009806246,"about_ca_topic_score_gemma":0.0162696,"domain_scores_codex":[0.9993092,0.00009308581,0.00007083648,0.0002069785,0.0002128791,0.0001070183],"domain_scores_gemma":[0.9994381,0.0001473694,0.00006125006,0.0001041245,0.0002194533,0.00002964795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005727349,0.000380063,0.004465967,0.0008596936,0.0003802657,0.001020873,0.0002911703,0.04060055,0.05071312,0.002558671,0.06292424,0.8352327],"study_design_scores_gemma":[0.00009463558,0.0004986079,0.005957764,0.00009648066,0.0002294058,0.001110038,0.0003493194,0.9181429,0.04297901,0.006995748,0.02342501,0.0001210831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2036722,0.004595357,0.746029,0.001015901,0.001325878,0.0005147005,0.01198867,0.02598206,0.004876127],"genre_scores_gemma":[0.5537246,0.002682566,0.3568927,0.0006422395,0.0005813232,0.0008904953,0.06716427,0.001576146,0.01584559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009806246,"threshold_uncertainty_score":0.01949835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0123174618960009,"score_gpt":0.2283517562152507,"score_spread":0.2160342943192498,"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."}}