{"id":"W4388787390","doi":"10.48550/arxiv.2311.09308","title":"Divergences between Language Models and Human Brains","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; James S. McDonnell Foundation","keywords":"Magnetoencephalography; Computer science; Human language; Narrative; Human brain; Process (computing); Psychology; Cognitive psychology; Natural language processing; Cognitive science; Artificial intelligence; Linguistics; Electroencephalography; Neuroscience","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006033457,0.0001250502,0.0001872229,0.00005607777,0.0004456583,0.0001513432,0.0003011223,0.000240665,0.00003336568],"category_scores_gemma":[0.0001060662,0.0001064039,0.00007340269,0.000123529,0.0001669498,0.0001726863,0.0004175973,0.0002341335,0.00001673351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007849539,"about_ca_system_score_gemma":0.00003298297,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03324316,"about_ca_topic_score_gemma":0.01206716,"domain_scores_codex":[0.9986881,0.0001254251,0.000150554,0.0003248636,0.0003352933,0.0003757899],"domain_scores_gemma":[0.9995186,0.00004166029,0.00009273727,0.0001533353,0.0000379781,0.0001556586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001026229,0.00007632341,0.08677208,0.0003609669,0.0005069751,0.00009692114,0.3852125,0.0002379833,0.0000325465,0.06472281,0.02220964,0.439761],"study_design_scores_gemma":[0.0001996415,0.00000805061,0.8811817,0.00004652593,0.0001390298,2.788836e-7,0.02366059,0.00002664177,0.00002719352,0.08866565,0.005417592,0.0006270932],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672495,0.0009507011,0.00005950552,0.001794635,0.0005463059,0.000937802,0.0000986122,0.00042192,0.02794105],"genre_scores_gemma":[0.9829849,0.0001907184,0.00002142335,0.00004952674,0.0008697006,0.0004759846,0.00009281298,0.00001171732,0.01530319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7944096,"threshold_uncertainty_score":0.9731945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1195529722328077,"score_gpt":0.3338850755295991,"score_spread":0.2143321032967915,"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."}}