{"id":"W4409764260","doi":"10.3390/electronics14091744","title":"LLM-Based Query Expansion with Gaussian Kernel Semantic Enhancement for Dense Retrieval","year":2025,"lang":"en","type":"article","venue":"Electronics","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Hubei Provincial Department of Education","keywords":"Query expansion; Computer science; Kernel (algebra); Information retrieval; Artificial intelligence; Natural language processing; Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003177471,0.0001564605,0.0001644747,0.0001234823,0.0001714004,0.0001149011,0.0004774386,0.00007590384,0.000005747859],"category_scores_gemma":[0.00004060725,0.0001279055,0.0000679606,0.0006043251,0.00004005218,0.0001634051,0.00004829158,0.0001530511,0.00000860287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002250326,"about_ca_system_score_gemma":0.0007389255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002413788,"about_ca_topic_score_gemma":0.0000086412,"domain_scores_codex":[0.9986785,0.00004161978,0.0002180403,0.0004109703,0.000246126,0.0004047113],"domain_scores_gemma":[0.9990493,0.00008894609,0.00009644174,0.0005498035,0.0001668381,0.00004865625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001105658,0.001170475,0.000171599,0.0004690501,0.0001591846,0.00001908534,0.0003588807,0.00003382978,0.3581447,0.4133705,0.007437961,0.2175592],"study_design_scores_gemma":[0.0005699732,0.0006976587,0.0000961057,0.00008233842,0.000020071,0.000002691837,0.000008844374,0.03165655,0.9343603,0.005405833,0.02690336,0.0001962288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006263425,0.001303135,0.9882874,0.00286746,0.00008896345,0.0004794284,0.00000111284,0.0002722838,0.0004367141],"genre_scores_gemma":[0.9432351,0.0002621221,0.05114471,0.001319966,0.00003801889,0.0001071507,0.00001645184,0.00001876967,0.003857726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9371428,"threshold_uncertainty_score":0.5215834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009439351382154772,"score_gpt":0.2593636279299072,"score_spread":0.2499242765477525,"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."}}