{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TFVYYAJUT3BEELW4S6BAFUG6OE","short_pith_number":"pith:TFVYYAJU","schema_version":"1.0","canonical_sha256":"996b8c01349ec2422edc978202d0de71360e1e031776eb3efdb856bbcb9a2e10","source":{"kind":"arxiv","id":"2605.15009","version":1},"attestation_state":"computed","paper":{"title":"DeepTokenEEG Enhancing Mild Cognitive Impairment and Alzheimers Classification via Tokenized EEG Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"DeepTokenEEG uses tokenized EEG features in a lightweight model to achieve up to 100% accuracy in Alzheimer's classification, outperforming prior methods by 1.41-15.35%.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bui Thanh Tung, Hung Cao, Huy-Dung Han, Khuong Vo, Manoj Vishwanath, Minh Long Ngo, Ngoc-Son Nguyen, Nguyen Quang Linh, Nguyen Thanh Vinh, Thinh Nguyen-Quang","submitted_at":"2026-05-14T16:10:03Z","abstract_excerpt":"The detection of Alzheimers disease (AD) is considered crucial, as timely intervention can improve patient outcomes. Electroencephalogram (EEG)-based diagnosis has been recognized as a non-invasive, accessible, and cost-effective approach for AD detection; however, it faces challenges related to data availability, accuracy of modern deep learning methods, and the time-consuming nature of expert-based interpretation. In this study, a novel lightweight and high-performance model, DeepTokenEEG, was designed for the diagnosis of AD and the classification of EEG signals from AD patients, individual"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T16:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"bf7fc9542c5cd80947c8d94a3ee32d30c998db742dbfbcf263b35f411cf2bb2f","abstract_canon_sha256":"c269306c3d04e7b348a6e0f90d22fc77dde3af7d1cdf33e25d9311a9e140bab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:54.804229Z","signature_b64":"a8qc5vpDDukDNjbPNEXEmp0UP4NP5u6P9YfHlDQUHUyFtgNw6duphgiZNefgZH/V0in8XIOwM9ZSJM4owlqJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"996b8c01349ec2422edc978202d0de71360e1e031776eb3efdb856bbcb9a2e10","last_reissued_at":"2026-05-17T23:38:54.803582Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:54.803582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepTokenEEG Enhancing Mild Cognitive Impairment and Alzheimers Classification via Tokenized EEG Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"DeepTokenEEG uses tokenized EEG features in a lightweight model to achieve up to 100% accuracy in Alzheimer's classification, outperforming prior methods by 1.41-15.35%.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bui Thanh Tung, Hung Cao, Huy-Dung Han, Khuong Vo, Manoj Vishwanath, Minh Long Ngo, Ngoc-Son Nguyen, Nguyen Quang Linh, Nguyen Thanh Vinh, Thinh Nguyen-Quang","submitted_at":"2026-05-14T16:10:03Z","abstract_excerpt":"The detection of Alzheimers disease (AD) is considered crucial, as timely intervention can improve patient outcomes. Electroencephalogram (EEG)-based diagnosis has been recognized as a non-invasive, accessible, and cost-effective approach for AD detection; however, it faces challenges related to data availability, accuracy of modern deep learning methods, and the time-consuming nature of expert-based interpretation. In this study, a novel lightweight and high-performance model, DeepTokenEEG, was designed for the diagnosis of AD and the classification of EEG signals from AD patients, individual"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"a novel lightweight and high-performance model, DeepTokenEEG, was designed for the diagnosis of AD and the classification of EEG signals from AD patients, individuals with other neurological conditions, and healthy subjects. ... achieves a maximum recorded accuracy of 100% on specific frequency bands, representing an improvement of 1.41-15.35% over state-of-the-art methods on the same dataset.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 100% accuracy on specific frequency bands generalizes beyond the 274-subject dataset (180 AD, 94 controls) and is not due to overfitting, data leakage, or unaccounted artifacts in the EEG recordings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DeepTokenEEG uses tokenized EEG features in a lightweight model to achieve up to 100% accuracy in Alzheimer's classification, outperforming prior methods by 1.41-15.35%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"fa102da633692dae6583da8d5b046479404f1603d9af5386dae9ad91ae1ff4ac"},"source":{"id":"2605.15009","kind":"arxiv","version":1},"verdict":{"id":"71c4e22a-c424-4fd4-997b-2efd2fb31980","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:19:43.052306Z","strongest_claim":"a novel lightweight and high-performance model, DeepTokenEEG, was designed for the diagnosis of AD and the classification of EEG signals from AD patients, individuals with other neurological conditions, and healthy subjects. ... achieves a maximum recorded accuracy of 100% on specific frequency bands, representing an improvement of 1.41-15.35% over state-of-the-art methods on the same dataset.","one_line_summary":"DeepTokenEEG uses tokenized EEG features in a lightweight model to achieve up to 100% accuracy in Alzheimer's classification, outperforming prior methods by 1.41-15.35%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 100% accuracy on specific frequency bands generalizes beyond the 274-subject dataset (180 AD, 94 controls) and is not due to overfitting, data leakage, or unaccounted artifacts in the EEG recordings.","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15009","created_at":"2026-05-17T23:38:54.803685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15009v1","created_at":"2026-05-17T23:38:54.803685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15009","created_at":"2026-05-17T23:38:54.803685+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFVYYAJUT3BE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFVYYAJUT3BEELW4","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFVYYAJU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE","json":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE.json","graph_json":"https://pith.science/api/pith-number/TFVYYAJUT3BEELW4S6BAFUG6OE/graph.json","events_json":"https://pith.science/api/pith-number/TFVYYAJUT3BEELW4S6BAFUG6OE/events.json","paper":"https://pith.science/paper/TFVYYAJU"},"agent_actions":{"view_html":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE","download_json":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE.json","view_paper":"https://pith.science/paper/TFVYYAJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15009&json=true","fetch_graph":"https://pith.science/api/pith-number/TFVYYAJUT3BEELW4S6BAFUG6OE/graph.json","fetch_events":"https://pith.science/api/pith-number/TFVYYAJUT3BEELW4S6BAFUG6OE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE/action/storage_attestation","attest_author":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE/action/author_attestation","sign_citation":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE/action/citation_signature","submit_replication":"https://pith.science/pith/TFVYYAJUT3BEELW4S6BAFUG6OE/action/replication_record"}},"created_at":"2026-05-17T23:38:54.803685+00:00","updated_at":"2026-05-17T23:38:54.803685+00:00"}