{"id":"W6949269119","doi":"10.5281/zenodo.14851367","title":"Code for Language models deconstruct the clinical intuition behind diagnosing autism","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"German legal, social, and political studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Intuition; Autism; Language model; Code (set theory); Natural language","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":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001293969,0.0001578008,0.0002510453,0.0001205711,0.003970549,0.0006418668,0.0008687893,0.0002413544,0.008706275],"category_scores_gemma":[0.002097467,0.0001409266,0.0001428892,0.0001884528,0.0009357591,0.00009834175,0.000511313,0.0003602578,0.001106521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001503504,"about_ca_system_score_gemma":0.00003090765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007318775,"about_ca_topic_score_gemma":0.0001810024,"domain_scores_codex":[0.9977403,0.0008128742,0.0002876664,0.0003639841,0.0003342365,0.0004609555],"domain_scores_gemma":[0.9988667,0.0003017321,0.0001563882,0.0002762045,0.0002563328,0.0001426254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007164874,0.00003644824,0.000001385896,0.00003745653,0.00006447444,0.000001872291,0.004064479,0.000001206388,8.013181e-7,0.2121034,0.7448264,0.03885489],"study_design_scores_gemma":[0.0002548035,0.00004214688,0.00004089425,0.00008922705,0.00005174083,0.000001451313,0.002244114,0.00003605383,0.000001720003,0.009911326,0.9871722,0.000154343],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000823205,0.0005257286,0.004432625,0.004351226,0.0005029478,0.0009239814,0.00144406,0.0006620092,0.9870751],"genre_scores_gemma":[0.1369655,0.005082353,0.001197767,0.003476801,0.006652182,0.000001950009,0.003340221,0.007882514,0.8354008],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2423458,"threshold_uncertainty_score":0.9996712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07926614499081669,"score_gpt":0.3675110942052571,"score_spread":0.2882449492144404,"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."}}