{"id":"W3184928878","doi":"10.1101/2021.07.26.453914","title":"Representational learning of brain responses in executive function and higher-order cognition using deep graph convolutions","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital; Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Courtois Foundation; Institut de Valorisation des Données","keywords":"Human Connectome Project; Cognition; Working memory; Computer science; Decoding methods; Graph; Power graph analysis; Neuroimaging; Cognitive model; Neural decoding; Sensory system; Convolutional neural network; Executive functions; Artificial intelligence; Cognitive psychology; Psychology; Neuroscience; Theoretical computer science; Functional connectivity; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006988039,0.0004908738,0.0003945766,0.0004910577,0.0001682499,0.0007362573,0.000652176,0.0005611615,0.001345969],"category_scores_gemma":[0.002514477,0.000269171,0.0008098215,0.0004678284,0.000660766,0.001180913,0.0007949697,0.001238173,0.000257455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006003344,"about_ca_system_score_gemma":0.0004924853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002754234,"about_ca_topic_score_gemma":0.002973207,"domain_scores_codex":[0.9998473,0.00005309813,0.000006647443,0.00004427238,0.00002254793,0.00002605448],"domain_scores_gemma":[0.9992403,0.0004444806,0.0001091892,0.00008629791,0.00005631558,0.00006338027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003179806,0.000182794,0.00665164,0.0001363599,0.0002548558,0.0001676072,0.0001829382,0.7798086,0.02918326,0.03282783,0.001660074,0.1486261],"study_design_scores_gemma":[0.000002528878,0.00001464448,0.0007585685,0.000003083492,0.000005081222,0.0000104455,0.000005531617,0.9858642,0.001255295,0.01196497,0.0001102508,0.000005364941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2062611,0.0003640074,0.7907691,0.0004944404,0.00004109935,0.00002321522,0.0001658431,0.0005735193,0.001307692],"genre_scores_gemma":[0.9450302,0.0002819676,0.05254738,0.00008406633,0.00002808082,0.0000307629,0.0002207523,0.00007034255,0.001706442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002754234,"threshold_uncertainty_score":0.005476356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03958499591156156,"score_gpt":0.2661328435786783,"score_spread":0.2265478476671167,"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."}}