{"id":"W6891814752","doi":"10.48448/3hrs-pw98","title":"Bag-of-Words Baselines for Semantic Code Search","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language; Code (set theory); Semantic search; Source code; Lexical analysis; Task (project management); Natural language user interface; Semantic computing","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":[0.006739233,0.00269214,0.00287364,0.008400373,0.00193165,0.00264063,0.003938921,0.003503693,0.01277453],"category_scores_gemma":[0.02130499,0.000489975,0.001853967,0.006471634,0.00132991,0.01007848,0.002647811,0.002783888,0.01121979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00222562,"about_ca_system_score_gemma":0.002892332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0183749,"about_ca_topic_score_gemma":0.02199346,"domain_scores_codex":[0.9943535,0.001767868,0.0004359833,0.001305613,0.001667961,0.000469133],"domain_scores_gemma":[0.9915234,0.003988863,0.0004362923,0.002049961,0.001613579,0.0003879531],"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":[0.005219579,0.002633411,0.005448421,0.002231501,0.000755101,0.0002371148,0.0002603993,0.04360362,0.01147976,0.008363808,0.09941477,0.8203525],"study_design_scores_gemma":[0.0006837133,0.002057153,0.008347838,0.0002828754,0.0004470994,0.0006296152,0.0007192845,0.8909633,0.02056385,0.03621757,0.03884546,0.0002422688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3775699,0.06356487,0.3881274,0.004419081,0.005274567,0.00221445,0.03228247,0.06277896,0.06376816],"genre_scores_gemma":[0.6472879,0.004343361,0.263467,0.0013658,0.001276669,0.001227453,0.05792788,0.002106881,0.02099707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0183749,"threshold_uncertainty_score":0.04273504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06799016076969057,"score_gpt":0.3739464263495497,"score_spread":0.3059562655798591,"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."}}