{"id":"W4302016045","doi":"10.36227/techrxiv.21235593","title":"Byte-Pair Encoding for classifying routine clinical electroencephalograms in adults over the lifespan","year":2022,"lang":"en","type":"preprint","venue":"","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; National Research Council Canada; Fraser Health","funders":"Alliance de recherche numérique du Canada","keywords":"Byte; Workflow; Electroencephalography; Encoding (memory); Computer science; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Machine learning; Neuroscience; Psychology; Database; Programming language","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":[0.0009179609,0.0005480261,0.000319154,0.001601695,0.0002587874,0.001106692,0.0004938624,0.000687668,0.002345507],"category_scores_gemma":[0.009431567,0.0001136498,0.0002727957,0.00126889,0.0002757677,0.001297247,0.0006014635,0.000523344,0.001402661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003800086,"about_ca_system_score_gemma":0.0006156752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001759666,"about_ca_topic_score_gemma":0.00146108,"domain_scores_codex":[0.9993609,0.0001963351,0.0001086948,0.0001972488,0.00009286637,0.00004396937],"domain_scores_gemma":[0.9955853,0.002784553,0.0003491316,0.000536169,0.0005980185,0.0001466825],"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":[0.001647539,0.000294902,0.03015514,0.0002312563,0.00006004626,0.000558676,0.0007023055,0.01101717,0.02257477,0.005467962,0.01037543,0.9169148],"study_design_scores_gemma":[0.0001540603,0.0008768296,0.0374883,0.0001733075,0.0001735831,0.002211972,0.001142505,0.794136,0.06914201,0.07397868,0.02040009,0.0001226281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.484072,0.001572692,0.482981,0.001889012,0.0004418909,0.00041299,0.01249199,0.01148733,0.004651103],"genre_scores_gemma":[0.7227144,0.0002737049,0.2690215,0.0001595443,0.0001262759,0.0001758479,0.006079817,0.0001541216,0.001294637],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002345507,"threshold_uncertainty_score":0.007846475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08596632434254743,"score_gpt":0.3698771348258035,"score_spread":0.2839108104832561,"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."}}