{"id":"W4406872811","doi":"10.1016/j.infsof.2025.107674","title":"XL-HQL: A HQL query generation method via XLNet and column attention","year":2025,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Column (typography); Computer science; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0002433747,0.00007811529,0.0001090138,0.0003964951,0.0001450649,0.0001252259,0.0001694543,0.0001788546,0.000002982979],"category_scores_gemma":[0.0001027575,0.00008055336,0.00001443505,0.0003122986,0.00003823974,0.0009196532,0.0001962073,0.0001178251,0.000007985214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002825715,"about_ca_system_score_gemma":0.00003620948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003496467,"about_ca_topic_score_gemma":0.00002887026,"domain_scores_codex":[0.9993684,0.00002365845,0.0002637386,0.0001434975,0.00007902193,0.0001216859],"domain_scores_gemma":[0.9995279,0.00003175419,0.00008493552,0.0002427266,0.00008996152,0.00002269488],"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":[0.000001350392,0.000004794455,0.002823546,0.00002751802,0.000007910946,4.610719e-7,0.0002145396,0.0000715708,0.000204553,0.09382126,0.0003922598,0.9024302],"study_design_scores_gemma":[0.0006887955,0.00006397653,0.004795414,0.00003542217,0.00001258645,0.00006894436,0.0001191798,0.9249142,0.0009954376,0.04288215,0.02520527,0.0002186521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03489989,0.0001329358,0.9614727,0.002422002,0.0001931491,0.0001502299,0.000001153741,0.0005370742,0.0001908911],"genre_scores_gemma":[0.4097928,0.0000680716,0.5884604,0.001439223,0.00001859082,0.00004873195,0.00001742547,0.000002904181,0.0001518159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9248426,"threshold_uncertainty_score":0.3284871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008798551029385699,"score_gpt":0.2539176403397022,"score_spread":0.2451190893103165,"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."}}