{"id":"W4409291146","doi":"10.31234/osf.io/rfwgd_v1","title":"Bigger is not always better: The importance of human-scale language modeling for psycholinguistics","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":1,"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":[0.005973766,0.0006839627,0.0009909812,0.000511262,0.0008620795,0.00335042,0.00135452,0.001225444,0.004266534],"category_scores_gemma":[0.03442147,0.0005212819,0.0004536826,0.0008825491,0.004104035,0.01280368,0.0026016,0.003694244,0.002000155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009964302,"about_ca_system_score_gemma":0.001465992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003874861,"about_ca_topic_score_gemma":0.003352958,"domain_scores_codex":[0.9973873,0.001494523,0.00007490594,0.0005684743,0.0003898908,0.0000848853],"domain_scores_gemma":[0.9844787,0.01029558,0.0003881026,0.003319271,0.0009069415,0.0006114274],"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":[0.001022144,0.0003996349,0.01489177,0.001027614,0.000261038,0.0003515127,0.005138923,0.09277169,0.03423779,0.2798154,0.06705767,0.5030247],"study_design_scores_gemma":[0.00007564647,0.0001056959,0.003857409,0.00008503717,0.00002709214,0.0002053333,0.0008268486,0.2873714,0.009054677,0.6672786,0.03102931,0.00008289152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1454741,0.005092409,0.7375706,0.07834441,0.0009278849,0.0001098273,0.0009198909,0.005765175,0.02579563],"genre_scores_gemma":[0.687488,0.001792461,0.3015672,0.002878039,0.0004789302,0.0001778464,0.0007583256,0.001385038,0.003474157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005973766,"threshold_uncertainty_score":0.03159273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08446958284889626,"score_gpt":0.3756931367693776,"score_spread":0.2912235539204813,"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."}}