{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004660524,0.001575261,0.001081477,0.0008054233,0.0006803874,0.001695591,0.002250608,0.001593961,0.007519622],"category_scores_gemma":[0.02318634,0.0005938279,0.0009122365,0.0009356876,0.0007601025,0.003937832,0.001923534,0.003234416,0.005084069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332764,"about_ca_system_score_gemma":0.001553074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008154227,"about_ca_topic_score_gemma":0.01294368,"domain_scores_codex":[0.9976838,0.001088125,0.0001360666,0.0005935992,0.0003315757,0.0001668013],"domain_scores_gemma":[0.9902679,0.00723428,0.0001565937,0.001382717,0.0007047197,0.0002537042],"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":[0.001978515,0.001301956,0.007358773,0.001927735,0.0004547445,0.0006936311,0.00113231,0.2395132,0.03309617,0.01309238,0.08024541,0.6192051],"study_design_scores_gemma":[0.0003086975,0.0005621959,0.001639859,0.00007080932,0.00007845303,0.0003395432,0.0004030388,0.9519799,0.01860646,0.009185368,0.01676496,0.00006077414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2878713,0.005826402,0.5917907,0.002454331,0.000774943,0.0009878116,0.005643936,0.08583393,0.01881663],"genre_scores_gemma":[0.6390768,0.0008789517,0.3296431,0.001691343,0.0002262664,0.0008344257,0.01527115,0.004228711,0.008149405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008154227,"threshold_uncertainty_score":0.02515566,"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."}}