{"id":"W7106828477","doi":"10.48448/f0wv-br78","title":"SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Metadata; Pipeline (software); Quality (philosophy); Task (project management); Natural language generation; Citation; Key (lock)","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":[0.01023368,0.001587721,0.0009303937,0.00727522,0.0008951673,0.002686555,0.002308797,0.001472099,0.009648764],"category_scores_gemma":[0.0484943,0.0007405056,0.001635039,0.004800522,0.0006620709,0.003242432,0.004142603,0.001440996,0.01131075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167077,"about_ca_system_score_gemma":0.004963491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003808552,"about_ca_topic_score_gemma":0.01188513,"domain_scores_codex":[0.9926555,0.003791058,0.0008715185,0.001235745,0.001207741,0.000238472],"domain_scores_gemma":[0.9652357,0.01871627,0.002202481,0.008169251,0.004598614,0.001077693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006071508,0.0004107058,0.01746372,0.004577918,0.0003036087,0.000292058,0.001546093,0.008769862,0.01263557,0.009040653,0.5800897,0.3642629],"study_design_scores_gemma":[0.0012256,0.0006773368,0.0182774,0.0007014301,0.0002436365,0.0006957975,0.001763545,0.2472396,0.03538797,0.04603303,0.6473866,0.0003681287],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.04533515,0.004067018,0.3816549,0.00331074,0.001111172,0.003501035,0.3190722,0.2302187,0.01172899],"genre_scores_gemma":[0.07603443,0.0009020438,0.4499227,0.001214827,0.0002410417,0.003952336,0.4574749,0.004011249,0.00624653],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01023368,"threshold_uncertainty_score":0.05412155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1586126533183793,"score_gpt":0.3941692993624326,"score_spread":0.2355566460440533,"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."}}