{"id":"W4403586008","doi":"10.48550/arxiv.2409.03888","title":"CALM: Cognitive Assessment using Light-insensitive Model","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Color perception and design","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cognition; Computer science; Cognitive psychology; Environmental science; Psychology; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002450266,0.0004489531,0.0004608411,0.0004564879,0.0001559494,0.00008091966,0.0002922898,0.0006138763,0.001383204],"category_scores_gemma":[0.00001300858,0.0005275002,0.0003709834,0.0003979273,0.0001473283,0.00006543445,0.000955288,0.001340089,0.001450493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006139659,"about_ca_system_score_gemma":0.0004516261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003605068,"about_ca_topic_score_gemma":0.00008310292,"domain_scores_codex":[0.9974553,0.000318674,0.0002493681,0.001425573,0.000108673,0.0004424176],"domain_scores_gemma":[0.998644,0.000124565,0.0001724842,0.0005773651,0.0002569942,0.0002246167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001744177,0.001639322,0.001901004,0.0004666098,0.003619222,0.01527058,0.0157481,0.3942343,0.002884219,0.543296,0.01705411,0.002142407],"study_design_scores_gemma":[0.001100366,0.0001109588,0.001751388,0.0003617401,0.001097865,0.00003393329,0.004538567,0.9405876,0.00004084707,0.04920199,0.0002073993,0.0009673513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7342021,0.00006464316,0.1345998,0.0001000723,0.001448548,0.0005758092,0.0001898418,0.0003258002,0.1284933],"genre_scores_gemma":[0.9807712,0.00003144106,0.0003131891,0.0003087654,0.0001810658,0.000003141343,0.0000536697,0.0000638975,0.01827363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5463533,"threshold_uncertainty_score":0.9997177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2156942703408742,"score_gpt":0.298900751318162,"score_spread":0.0832064809772878,"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."}}