{"id":"W3105973574","doi":"10.1177/10597123221085039","title":"From eye-blinks to state construction: Diagnostic benchmarks for online representation learning","year":2022,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Alberta Machine Intelligence Institute; Alberta Innovates - Technology Futures; DeepMind; University of Warwick; Canadian Institute for Advanced Research; Princeton University","keywords":"Construct (python library); Computer science; Machine learning; Artificial intelligence; Representation (politics); Replicate; Scalability; Isolation (microbiology); Feature learning; Focus (optics); State (computer science); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001593562,0.0001421848,0.0001748238,0.00009664219,0.0005964502,0.0001091546,0.0005279997,0.00002951764,0.00008210489],"category_scores_gemma":[0.00009639854,0.0001466226,0.00009235556,0.0004555515,0.00002945149,0.000222915,0.0007378025,0.0003668017,0.000004834329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008246251,"about_ca_system_score_gemma":0.00004806562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002352805,"about_ca_topic_score_gemma":0.0000270946,"domain_scores_codex":[0.9983972,0.0001576342,0.0002741965,0.0005613754,0.0003073921,0.0003021863],"domain_scores_gemma":[0.9986439,0.0006770661,0.0001449458,0.0002987066,0.0001171229,0.000118248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001265288,0.0003527619,0.02659532,0.00000471893,0.00004648455,0.0001721064,0.002023473,0.4111217,0.001482808,0.001266969,0.00302224,0.5537849],"study_design_scores_gemma":[0.003236528,0.003297108,0.1965183,0.0001005421,0.0001591382,0.00007967834,0.003490222,0.7531168,0.002069992,0.00475659,0.03166358,0.001511539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7270492,0.00006724974,0.270197,0.000791234,0.001084481,0.0006228233,0.00005922636,0.0001034701,0.00002530823],"genre_scores_gemma":[0.888373,0.000005478706,0.1102393,0.0002110681,0.0003285592,0.0003577595,0.000162963,0.00001656362,0.000305316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5522734,"threshold_uncertainty_score":0.5979097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03177940212657503,"score_gpt":0.3003316442463452,"score_spread":0.2685522421197701,"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."}}