{"id":"W4416017155","doi":"10.1145/3746252.3760960","title":"Study on LLMs for Promptagator-Style Dense Retriever Training","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Work (physics); Code (set theory); Training (meteorology); Risk assessment; Government (linguistics)","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":[0.001389513,0.0003859809,0.000499553,0.0002779014,0.0004568175,0.0005118973,0.001318028,0.0001708309,0.00006099384],"category_scores_gemma":[0.0004210529,0.000366263,0.0001966975,0.0008383366,0.00005108348,0.0003731311,0.0004995877,0.0003303163,0.00005068825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001616443,"about_ca_system_score_gemma":0.0005915866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002606669,"about_ca_topic_score_gemma":0.00002149804,"domain_scores_codex":[0.9963479,0.0001526253,0.0007748954,0.00142585,0.0005237467,0.000774951],"domain_scores_gemma":[0.997532,0.0004500693,0.0001440882,0.001469386,0.000236238,0.0001682468],"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":[0.000333698,0.002698127,0.004577856,0.0002214371,0.0005942634,0.000108388,0.0852878,0.001775937,0.0004185796,0.3386261,0.007469492,0.5578883],"study_design_scores_gemma":[0.005851292,0.002630675,0.00501544,0.0004041519,0.0001458958,0.000007554474,0.01251311,0.952214,0.002394996,0.007105796,0.0106764,0.001040683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.225865,0.00008179281,0.7566355,0.001941685,0.002331128,0.002543262,0.000003294338,0.0002022092,0.01039606],"genre_scores_gemma":[0.9514425,0.000002396135,0.02911525,0.001596774,0.0001840349,0.0001336008,6.338421e-7,0.00002031713,0.01750448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9504381,"threshold_uncertainty_score":0.9998789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09112275622836809,"score_gpt":0.3256828668712164,"score_spread":0.2345601106428484,"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."}}