{"id":"W2883195769","doi":"10.1109/icsme.2018.00057","title":"Effective Reformulation of Query for Code Search Using Crowdsourced Knowledge and Extra-Large Data Analytics","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Information retrieval; Code (set theory); Search engine; Web search query; Semantic search; Relevance (law); Query expansion; Programming language","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":[0.00726889,0.002014244,0.002640672,0.008596272,0.001891133,0.003280181,0.003229929,0.002453023,0.003300291],"category_scores_gemma":[0.03391303,0.0006919773,0.001621834,0.006807096,0.002039396,0.006490489,0.006024098,0.002062465,0.00235996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002557932,"about_ca_system_score_gemma":0.005473096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02157212,"about_ca_topic_score_gemma":0.02525841,"domain_scores_codex":[0.9867586,0.005121518,0.0009187917,0.002796866,0.003786755,0.0006173767],"domain_scores_gemma":[0.9782563,0.01217088,0.001166283,0.004436265,0.003358634,0.0006115693],"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":[0.001363753,0.001414137,0.009458874,0.002584224,0.0003439313,0.001023129,0.005461299,0.08383508,0.04784443,0.02652795,0.06102479,0.7591184],"study_design_scores_gemma":[0.0002319171,0.000356663,0.003487593,0.000112706,0.0001417058,0.0003432573,0.00283853,0.8938671,0.01706658,0.05835397,0.02305284,0.0001471204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07771035,0.001586215,0.8913848,0.002611485,0.000201393,0.001333289,0.004625179,0.01462726,0.005920085],"genre_scores_gemma":[0.4645137,0.0004735758,0.5163541,0.0008704596,0.0002274428,0.001010465,0.01226962,0.0007233085,0.003557355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02157212,"threshold_uncertainty_score":0.04289311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1315202075538539,"score_gpt":0.3966857943397065,"score_spread":0.2651655867858526,"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."}}