{"id":"W3203911409","doi":"10.1145/3465403","title":"CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Programming language; Semantics (computer science); Information retrieval; Natural language processing","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":[0.0007698426,0.001442428,0.001120218,0.004536153,0.0005774433,0.001123477,0.002385695,0.001095274,0.003001688],"category_scores_gemma":[0.005258622,0.0005577006,0.001066542,0.002888831,0.000784746,0.004594875,0.002014129,0.001003969,0.001512798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001075367,"about_ca_system_score_gemma":0.00244243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0155304,"about_ca_topic_score_gemma":0.02363176,"domain_scores_codex":[0.9987949,0.0001145237,0.0001027578,0.0004597894,0.000441239,0.00008674254],"domain_scores_gemma":[0.9985311,0.0005212316,0.0001940762,0.0003129288,0.0003471957,0.00009348483],"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":[0.001081302,0.0004694634,0.01876595,0.001477344,0.0002034928,0.000585572,0.0008776906,0.03997193,0.05615087,0.01582817,0.03782484,0.8267633],"study_design_scores_gemma":[0.0001222021,0.0003842803,0.00398792,0.00006098612,0.0001030929,0.0006185941,0.0002730038,0.9161671,0.03794076,0.01814334,0.02212013,0.0000785571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1780628,0.00297011,0.725131,0.0009161563,0.0001584717,0.0009104634,0.00716982,0.07825727,0.006423918],"genre_scores_gemma":[0.4117323,0.0009371737,0.5618519,0.0006147695,0.00005592271,0.0005585089,0.0153215,0.001672027,0.007255972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0155304,"threshold_uncertainty_score":0.03088003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08444068339043621,"score_gpt":0.3254469426044706,"score_spread":0.2410062592140344,"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."}}