{"id":"W7077911890","doi":"10.48448/7ydn-np56","title":"ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Operationalization; Leverage (statistics); Pace; Language model; Scientific literature; Readability; Natural language generation","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004866698,0.0003725812,0.0003271781,0.003416443,0.001225173,0.004022599,0.003550889,0.0002747174,0.0001702721],"category_scores_gemma":[0.0002171586,0.0002909625,0.00005723105,0.006193649,0.001062959,0.001545128,0.001641575,0.00112584,0.00008858485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000340258,"about_ca_system_score_gemma":0.002697515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002333798,"about_ca_topic_score_gemma":0.001034991,"domain_scores_codex":[0.9925864,0.0003380098,0.0003434528,0.002161078,0.003305091,0.001265947],"domain_scores_gemma":[0.9959676,0.0001058991,0.0001510458,0.002340976,0.001160801,0.0002736573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008831275,0.0001834421,0.00001527488,0.0001407302,0.00003933504,0.0002314243,0.008336153,0.00169201,0.003158587,0.8040434,0.1708105,0.01134041],"study_design_scores_gemma":[0.000408418,0.0000854136,0.000005169694,0.0006924623,0.000006018134,0.00001131824,0.000188165,0.9593698,0.0007838996,0.005887683,0.03215222,0.0004094301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0002962729,0.00278968,0.7865345,0.0007593066,0.0009153636,0.000870523,0.0001241755,0.0003567443,0.2073534],"genre_scores_gemma":[0.061453,0.0000973498,0.1349661,0.0004364909,0.0008910028,0.00008878991,0.0001932832,0.0001476469,0.8017263],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9576778,"threshold_uncertainty_score":0.9999542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06560478267328029,"score_gpt":0.3721665830719578,"score_spread":0.3065618003986775,"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."}}