{"id":"W4413082047","doi":"10.2139/ssrn.5339141","title":"Large Language Models Improve Hypothesis Generation by Reducing Effort","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Quest University Canada; University of Toronto","funders":"","keywords":"Computer science; Linguistics; Philosophy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02110489,0.003415752,0.00290129,0.004961308,0.001688228,0.004719095,0.003189833,0.005145378,0.01254542],"category_scores_gemma":[0.1329641,0.001723889,0.003222737,0.00299485,0.001217733,0.009168262,0.004966972,0.006187821,0.00906282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007901298,"about_ca_system_score_gemma":0.002471498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001633182,"about_ca_topic_score_gemma":0.003809836,"domain_scores_codex":[0.9835384,0.01143853,0.0008151602,0.002294,0.001538008,0.0003757519],"domain_scores_gemma":[0.7508479,0.2295779,0.002327877,0.01174602,0.003927434,0.001572877],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004020149,0.001886758,0.02336787,0.001010182,0.001958349,0.000855222,0.0006800335,0.1043409,0.01872061,0.007844022,0.03455884,0.8007571],"study_design_scores_gemma":[0.0007511502,0.0006205958,0.004390478,0.0001116595,0.001324672,0.0003487023,0.000199789,0.9264669,0.008642817,0.05133743,0.005712885,0.00009293462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09741589,0.003179969,0.8720504,0.00484171,0.0009869507,0.0008602092,0.001951741,0.01279379,0.0059193],"genre_scores_gemma":[0.6318802,0.001242103,0.3400844,0.003259973,0.002135066,0.001109508,0.008834507,0.002294307,0.009159953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9788951,"threshold_uncertainty_score":0.1116146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01425321630413385,"score_gpt":0.2468350027638569,"score_spread":0.232581786459723,"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."}}