{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7HM6CKVFP3CDPYCX6L5O4A7MYV","short_pith_number":"pith:7HM6CKVF","schema_version":"1.0","canonical_sha256":"f9d9e12aa57ec437e057f2faee03ecc56e736bcec67edfbbb53b6a2781fd399e","source":{"kind":"arxiv","id":"2409.00121","version":1},"attestation_state":"computed","paper":{"title":"BELT-2: Bootstrapping EEG-to-Language representation alignment for multi-task brain decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"eess.SP","authors_text":"Chin-Teng Lin, Fred Chang, Jinzhao Zhou, Thomas Do, Yiqun Duan, Yu-Kai Wang","submitted_at":"2024-08-28T12:30:22Z","abstract_excerpt":"The remarkable success of large language models (LLMs) across various multi-modality applications is well established. However, integrating large language models with humans, or brain dynamics, remains relatively unexplored. In this paper, we introduce BELT-2, a pioneering multi-task model designed to enhance both encoding and decoding performance from EEG signals. To bolster the quality of the EEG encoder, BELT-2 is the first work to innovatively 1) adopt byte-pair encoding (BPE)-level EEG-language alignment and 2) integrate multi-task training and decoding in the EEG domain. Inspired by the "},"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":"2409.00121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2024-08-28T12:30:22Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"e3667713c981a6549c4e24aed6329e849817aa7ebb4a5f842f1a763633cf8ee6","abstract_canon_sha256":"21a8e12ce2fe8fb35b9234d53a32305f81c2ac821d54111f1bf5ddd48dbc0763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:41.132073Z","signature_b64":"h+EH2Y9AcPYOv20psHcWEaQGN14FYWdr8mcWywrVTh2bAaRN5vEcOGryhacVqS4T8tGgWG5WL7Blk9qfqku4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d9e12aa57ec437e057f2faee03ecc56e736bcec67edfbbb53b6a2781fd399e","last_reissued_at":"2026-07-05T09:01:41.131615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:41.131615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BELT-2: Bootstrapping EEG-to-Language representation alignment for multi-task brain decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"eess.SP","authors_text":"Chin-Teng Lin, Fred Chang, Jinzhao Zhou, Thomas Do, Yiqun Duan, Yu-Kai Wang","submitted_at":"2024-08-28T12:30:22Z","abstract_excerpt":"The remarkable success of large language models (LLMs) across various multi-modality applications is well established. However, integrating large language models with humans, or brain dynamics, remains relatively unexplored. In this paper, we introduce BELT-2, a pioneering multi-task model designed to enhance both encoding and decoding performance from EEG signals. To bolster the quality of the EEG encoder, BELT-2 is the first work to innovatively 1) adopt byte-pair encoding (BPE)-level EEG-language alignment and 2) integrate multi-task training and decoding in the EEG domain. Inspired by the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00121","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.00121/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.00121","created_at":"2026-07-05T09:01:41.131673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00121v1","created_at":"2026-07-05T09:01:41.131673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00121","created_at":"2026-07-05T09:01:41.131673+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HM6CKVFP3CD","created_at":"2026-07-05T09:01:41.131673+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HM6CKVFP3CDPYCX","created_at":"2026-07-05T09:01:41.131673+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HM6CKVF","created_at":"2026-07-05T09:01:41.131673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.22197","citing_title":"Neural Signals Generate Clinical Notes in the Wild","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10172","citing_title":"Wearable AI in the Era of Large Sensor Models","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV","json":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV.json","graph_json":"https://pith.science/api/pith-number/7HM6CKVFP3CDPYCX6L5O4A7MYV/graph.json","events_json":"https://pith.science/api/pith-number/7HM6CKVFP3CDPYCX6L5O4A7MYV/events.json","paper":"https://pith.science/paper/7HM6CKVF"},"agent_actions":{"view_html":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV","download_json":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV.json","view_paper":"https://pith.science/paper/7HM6CKVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00121&json=true","fetch_graph":"https://pith.science/api/pith-number/7HM6CKVFP3CDPYCX6L5O4A7MYV/graph.json","fetch_events":"https://pith.science/api/pith-number/7HM6CKVFP3CDPYCX6L5O4A7MYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV/action/storage_attestation","attest_author":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV/action/author_attestation","sign_citation":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV/action/citation_signature","submit_replication":"https://pith.science/pith/7HM6CKVFP3CDPYCX6L5O4A7MYV/action/replication_record"}},"created_at":"2026-07-05T09:01:41.131673+00:00","updated_at":"2026-07-05T09:01:41.131673+00:00"}