{"id":"W4302016048","doi":"10.36227/techrxiv.21235593.v1","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":"National Research Council Canada; Fraser Health; Simon Fraser University","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; Programming language; Database","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":[0.001086387,0.0006077127,0.0003471143,0.001745727,0.0002848246,0.001142681,0.0004989557,0.0007032479,0.002005214],"category_scores_gemma":[0.01096214,0.0001097756,0.000275293,0.001379026,0.0003077518,0.00145388,0.0006024623,0.0005498627,0.001382528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003616128,"about_ca_system_score_gemma":0.0006722208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001333614,"about_ca_topic_score_gemma":0.001114902,"domain_scores_codex":[0.9991767,0.0002612982,0.0001429065,0.0002411215,0.0001239533,0.00005396202],"domain_scores_gemma":[0.9944574,0.003632825,0.0004308838,0.00061428,0.0006931851,0.0001714711],"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":[0.00178778,0.0003105445,0.02888215,0.0003079371,0.00005888992,0.0007333649,0.0008467528,0.01199963,0.02555633,0.007033025,0.009525794,0.9129578],"study_design_scores_gemma":[0.0001600537,0.001006074,0.03560643,0.0002153583,0.0001947822,0.003307235,0.001328744,0.7493909,0.08011929,0.1021927,0.02633715,0.0001413196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4289105,0.001735652,0.5435089,0.001618605,0.0004238187,0.0003912801,0.009762963,0.009133099,0.004515069],"genre_scores_gemma":[0.7110345,0.0003389172,0.2814031,0.0001535475,0.0001400102,0.0001863768,0.005365578,0.0001552432,0.001222644],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002005214,"threshold_uncertainty_score":0.006708145,"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."}}