{"id":"W4382468395","doi":"10.1609/aaai.v37i7.25952","title":"Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Electroencephalography; Computer science; Epileptic seizure; Artificial intelligence; Set (abstract data type); Machine learning; Pattern recognition (psychology); Data set; Psychology; Neuroscience","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":[0.0004971537,0.000193566,0.0002694644,0.0006648295,0.000227669,0.0001389821,0.000772433,0.00009163297,0.000008996068],"category_scores_gemma":[0.0005035095,0.0001606659,0.0001645872,0.003827807,0.00007483619,0.0001770859,0.0001513187,0.0002414945,0.00006231212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004477336,"about_ca_system_score_gemma":0.00002444916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004145511,"about_ca_topic_score_gemma":0.00005313474,"domain_scores_codex":[0.998214,0.00002874755,0.0004473416,0.0006312811,0.0003147447,0.000363882],"domain_scores_gemma":[0.9990854,0.0002094342,0.0002195342,0.0001513482,0.0002629323,0.00007131688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001908202,0.0001470103,0.0004848122,0.0001019342,0.00003267016,4.399126e-7,0.004933706,0.007108212,0.9128186,0.02179177,0.00003754059,0.0523525],"study_design_scores_gemma":[0.00002053531,0.0001572315,0.0003124424,0.0000340708,0.00002525743,6.62033e-7,0.0006232399,0.4127779,0.5754759,0.01039749,0.00005809344,0.0001171885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775677,0.000003271793,0.01902601,0.001396024,0.0002232446,0.0009919294,0.000006783672,0.0002344342,0.0005506556],"genre_scores_gemma":[0.9990767,0.00001861164,0.0002854462,0.0002002713,0.0000445748,0.000224657,0.000001163944,0.00001712377,0.0001314762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4056697,"threshold_uncertainty_score":0.6551763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06144156666841157,"score_gpt":0.3034914100998463,"score_spread":0.2420498434314347,"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."}}