{"id":"W3137420038","doi":"10.1101/2021.03.10.434856","title":"Explanatory latent representation of heterogeneous spatial maps of task-fMRI in large-scale datasets","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"","keywords":"Human Connectome Project; Representation (politics); Computer science; Autoencoder; Latent variable; Artificial intelligence; Task (project management); Machine learning; Multivariate statistics; Generalization; Pattern recognition (psychology); Deep learning; Psychology; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003091393,0.0005619547,0.0004523025,0.0008950023,0.0002405417,0.0008523774,0.0007300009,0.0007238797,0.0008338181],"category_scores_gemma":[0.007590923,0.0003314631,0.0008559631,0.0007922624,0.0008672878,0.0009948821,0.0008710415,0.001579563,0.0001893932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007861198,"about_ca_system_score_gemma":0.0005872558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004587092,"about_ca_topic_score_gemma":0.006599972,"domain_scores_codex":[0.9994639,0.0002581216,0.00002270103,0.0001645133,0.00004287127,0.00004788601],"domain_scores_gemma":[0.9954081,0.003063223,0.0004816091,0.0006674789,0.0002761014,0.0001033466],"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":[0.0002824044,0.0001958116,0.02089386,0.0001078355,0.000240426,0.0001899796,0.0002784547,0.9000411,0.01125637,0.01255043,0.002551422,0.05141194],"study_design_scores_gemma":[0.00000582237,0.00001066308,0.003926002,0.000006589146,0.000008174503,0.00001497328,0.00001379772,0.9890742,0.000697712,0.006083828,0.0001492348,0.000009043675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5073258,0.0002579008,0.4882923,0.0007986763,0.00002414838,0.00004309474,0.001893647,0.0008627498,0.0005016613],"genre_scores_gemma":[0.96641,0.00008877447,0.03077702,0.00006060074,0.00002260598,0.0000635449,0.001962911,0.00007096216,0.0005436727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004587092,"threshold_uncertainty_score":0.01634908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02724078081454626,"score_gpt":0.2484794217903512,"score_spread":0.2212386409758049,"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."}}