{"id":"W4409291343","doi":"10.31234/osf.io/rfwgd_v2","title":"Bigger is not always better: The importance of human-scale language modeling for psycholinguistics","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Psycholinguistics; Scale (ratio); Linguistics; Computer science; Cognitive science; Natural language processing; Psychology; Philosophy; Geography; Cognition; Neuroscience; Cartography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005956451,0.0006826258,0.0009912665,0.000510281,0.0008598816,0.003347336,0.001351645,0.00122499,0.004277479],"category_scores_gemma":[0.03430777,0.0005205582,0.0004530607,0.0008831287,0.004092526,0.01278012,0.002600872,0.0036878,0.001997055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009957412,"about_ca_system_score_gemma":0.001464947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003881664,"about_ca_topic_score_gemma":0.003362222,"domain_scores_codex":[0.9973949,0.001490384,0.00007466224,0.0005667896,0.0003887385,0.0000845884],"domain_scores_gemma":[0.984508,0.01026897,0.0003873092,0.003320777,0.0009046832,0.0006103305],"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":[0.001022258,0.0003990956,0.01480898,0.001028194,0.0002608325,0.0003519686,0.005121647,0.09303501,0.03436505,0.2802913,0.06676226,0.5025533],"study_design_scores_gemma":[0.00007550353,0.000105494,0.003845077,0.00008480287,0.00002705106,0.0002053969,0.000824065,0.28882,0.009092126,0.6658134,0.03102448,0.00008262852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1446823,0.005061656,0.7391363,0.07766107,0.0009210632,0.0001095991,0.0009170026,0.005767833,0.02574317],"genre_scores_gemma":[0.6868504,0.001785196,0.3022309,0.002857774,0.0004760684,0.0001772812,0.0007559789,0.001387363,0.003478975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005956451,"threshold_uncertainty_score":0.03150111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08219716216434357,"score_gpt":0.3792665452262622,"score_spread":0.2970693830619186,"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."}}