{"paper":{"title":"One-Block Transformer (1BT) for EEG-Based Cognitive Workload Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single cross-attention bottleneck inside a one-block transformer classifies EEG workload levels at under 0.5 million parameters.","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"eess.SP","authors_text":"Christian Arzate Cruz, Giorgos Giannakakis, Randy Gomez, Raul Fernandez Rojas, Stefanos Gkikas, Thomas Kassiotis","submitted_at":"2026-04-21T04:32:59Z","abstract_excerpt":"Accurate and continuous estimation of cognitive workload is fundamental to creating adaptive human-machine systems. However, designing architectures that balance representational capacity with computational efficiency has been challenging for practical deployment. This paper introduces 1BT, a One-Block Transformer for compact and efficient EEG-based cognitive workload assessment. The model aggregates multi-channel temporal sequences via a minimal latent bottleneck, using a single cross-attention module followed by lightweight self-attention. A controlled study involving 11 participants perform"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The final model achieves high workload classification performance with under 0.5 million parameters and 0.02 GFLOPs, paving the way for a design direction for real-time cognitive workload monitoring in resource-constrained settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the single cross-attention bottleneck and lightweight self-attention preserve enough information to accurately distinguish workload levels, and that results from 11 participants on three specific tasks will generalize to other people and real-world conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A minimal one-block transformer architecture classifies cognitive workload from EEG recordings with high accuracy while using under 0.5 million parameters and 0.02 GFLOPs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single cross-attention bottleneck inside a one-block transformer classifies EEG workload levels at under 0.5 million parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d707223d465a54cc560aad3b71ed45fd34566fcebc6755a89e3f72e24c535ab8"},"source":{"id":"2605.00856","kind":"arxiv","version":2},"verdict":{"id":"ac89838c-3e77-4b23-a60e-51217878e133","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T02:32:09.107295Z","strongest_claim":"The final model achieves high workload classification performance with under 0.5 million parameters and 0.02 GFLOPs, paving the way for a design direction for real-time cognitive workload monitoring in resource-constrained settings.","one_line_summary":"A minimal one-block transformer architecture classifies cognitive workload from EEG recordings with high accuracy while using under 0.5 million parameters and 0.02 GFLOPs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the single cross-attention bottleneck and lightweight self-attention preserve enough information to accurately distinguish workload levels, and that results from 11 participants on three specific tasks will generalize to other people and real-world conditions.","pith_extraction_headline":"A single cross-attention bottleneck inside a one-block transformer classifies EEG workload levels at under 0.5 million parameters."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00856/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}