{"paper":{"title":"Your Vision Foundation Model Is Secretly an EEG Foundation Model","arxiv_id":"2611.17031","primary_cat":"cs.AI","submitted_at":"2026-11-12T16:17:16+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.8,"id":"s0","own":false,"role":"background","text":"Electroencephalography (EEG) foundation models are pretrained on thousands of hours of recordings, yet their frozen features transfer poorly to downstream tasks, and this transfer does not consistently improve with larger models or more pretraining data.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.53,"role_probabilities":{"gap":0.2,"method":0.0,"result":0.0,"background":0.8,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.66,"id":"s1","own":true,"role":"result","text":"We show that a vision foundation model that has never seen EEG is a stronger frozen EEG encoder than these specialized models, once the signals are rendered as images that a vision transformer can read.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.9,"quantitative":true,"quantitative_p":0.88,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.66,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.34,"interpretation":0.0}},{"i":2,"p":0.86,"id":"s2","own":true,"role":"method","text":"Our method, SeeEEG, keeps the vision backbone frozen and learns only how EEG is displayed to it.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.81,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.86,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.14,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"method","text":"Each channel occupies a dedicated row of patches and is drawn either as a waveform at a fixed gain or as a scalogram whose frequency range spans the patch height, so that task-relevant patterns fall within individual tokens.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.84,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"method","text":"The montage, filtering, and contrast parameters of this display are initialized from a standard clinical montage and optimized with the task loss through the frozen backbone, which amounts to at most 1,113 trainable parameters per view.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"method","text":"We compare SeeEEG with seven EEG foundation models on eight clinical, sleep, affective, and brain-computer interface datasets, with every encoder frozen and paired with identical readout heads.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.97,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"With a frozen DINOv3 ViT-B, SeeEEG outperforms every EEG foundation model in balanced accuracy on all eight datasets and reaches a mean rank of 1.3 in Cohen kappa or AUROC, compared with 2.9 for the strongest baseline, REVE.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.58,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"The learned displays transfer without further optimization to the video encoder V-JEPA 2.1, which outperforms every EEG foundation model on both metrics on six of the eight datasets.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.15,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.63,"id":"s8","own":true,"role":"interpretation","text":"Replacing DINOv3 with a randomly initialized ViT-B lowers the score by 15.2 points on average, so the ability to read rendered EEG comes from visual pretraining.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.96,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.37,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.63}}]},"compiled":{"main_claim":{"p":1.0,"text":"We show that a vision foundation model that has never seen EEG is a stronger frozen EEG encoder than these specialized models, once the signals are rendered as images that a vision transformer can read.","location":"abstract s1","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7224,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.08,"states_limitation":0.39,"human_participants":0.73,"controlled_comparison":0.95,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.9,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.04,"observation_or_experiment":0.9,"simulation_or_computation":0.06}},"contribution_type":{"p":0.99,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.99,"empirical_study":0.01,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.51,"text":"Our method, SeeEEG, keeps the vision backbone frozen and learns only how EEG is displayed to it.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}