{"id":"W2911789761","doi":"10.1007/s10664-018-9671-0","title":"Automatic query reformulation for code search using crowdsourced knowledge","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Information retrieval; Web search query; Java; Code (set theory); Query expansion; Search engine; Web query classification; XPath; Precision and recall; Natural language; Programming language; World Wide Web; Artificial intelligence; XML; Set (abstract data type)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006851525,0.0002842212,0.0003415502,0.0003806327,0.0001117452,0.0001930593,0.0008666721,0.0001803721,0.00003595004],"category_scores_gemma":[0.001649196,0.0002835502,0.000160757,0.0009246418,0.00001664729,0.0005499979,0.0003780221,0.0003652312,0.0001522459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000502596,"about_ca_system_score_gemma":0.0001638807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001050425,"about_ca_topic_score_gemma":7.690562e-7,"domain_scores_codex":[0.9977182,0.00003884635,0.0003809631,0.0005886593,0.0004703883,0.0008029219],"domain_scores_gemma":[0.9964126,0.002342806,0.00004303825,0.0007674495,0.0001866172,0.0002475286],"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":[0.00001872656,0.0001657235,0.2202781,0.001530535,0.0001380464,0.00001758722,0.002220332,0.7500584,0.006509222,0.0008910924,0.0007799364,0.0173924],"study_design_scores_gemma":[0.0004622769,0.00007972159,0.04858326,0.0001203931,0.000005528124,0.00001788959,0.000005259923,0.9457414,0.00160523,0.00004397348,0.002970816,0.000364287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4600069,0.0001012681,0.5379918,0.00004589828,0.0003776962,0.000363984,0.000003312814,0.001101744,0.000007322029],"genre_scores_gemma":[0.7616457,0.000001198415,0.2378345,0.00003389843,0.000164817,0.00004921729,0.000008650658,0.00007244794,0.0001895618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3016388,"threshold_uncertainty_score":0.9999617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0489429157531969,"score_gpt":0.3347416356903026,"score_spread":0.2857987199371057,"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."}}