{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D6KEVUSPRDVBKIL2PI6QVAWCFJ","short_pith_number":"pith:D6KEVUSP","schema_version":"1.0","canonical_sha256":"1f944ad24f88ea15217a7a3d0a82c22a714f2d785c1e13de1f8bf3a1a10c6a4c","source":{"kind":"arxiv","id":"2502.17480","version":1},"attestation_state":"computed","paper":{"title":"Brain-to-Text Decoding: A Non-invasive Approach via Typing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"eess.SP","authors_text":"Hubert Banville, Jarod L\\'evy, Jean-R\\'emi King, J\\'er\\'emy Rapin, Mingfang Zhang, St\\'ephane d'Ascoli, Svetlana Pinet","submitted_at":"2025-02-18T08:36:46Z","abstract_excerpt":"Modern neuroprostheses can now restore communication in patients who have lost the ability to speak or move. However, these invasive devices entail risks inherent to neurosurgery. Here, we introduce a non-invasive method to decode the production of sentences from brain activity and demonstrate its efficacy in a cohort of 35 healthy volunteers. For this, we present Brain2Qwerty, a new deep learning architecture trained to decode sentences from either electro- (EEG) or magneto-encephalography (MEG), while participants typed briefly memorized sentences on a QWERTY keyboard. With MEG, Brain2Qwerty"},"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":"2502.17480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2025-02-18T08:36:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"7024a2549de6c7adda56a8ee5e3a30fb5390bb81186a7054e8b660aaeacafd62","abstract_canon_sha256":"50f50c84b4b1091cff10ee1cc1095c653777c65904d9d0952a42a183f4a73f71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:11.433080Z","signature_b64":"lrK1Kwa0/9kadg/C5W+m/g3PH5DkQYyNF9MIiEMvGWtff3ZjtT7xOG6MUkwPV95a9gHkElwe2hyaAVG/qlt5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f944ad24f88ea15217a7a3d0a82c22a714f2d785c1e13de1f8bf3a1a10c6a4c","last_reissued_at":"2026-07-05T10:19:11.432601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:11.432601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brain-to-Text Decoding: A Non-invasive Approach via Typing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"eess.SP","authors_text":"Hubert Banville, Jarod L\\'evy, Jean-R\\'emi King, J\\'er\\'emy Rapin, Mingfang Zhang, St\\'ephane d'Ascoli, Svetlana Pinet","submitted_at":"2025-02-18T08:36:46Z","abstract_excerpt":"Modern neuroprostheses can now restore communication in patients who have lost the ability to speak or move. However, these invasive devices entail risks inherent to neurosurgery. Here, we introduce a non-invasive method to decode the production of sentences from brain activity and demonstrate its efficacy in a cohort of 35 healthy volunteers. For this, we present Brain2Qwerty, a new deep learning architecture trained to decode sentences from either electro- (EEG) or magneto-encephalography (MEG), while participants typed briefly memorized sentences on a QWERTY keyboard. With MEG, Brain2Qwerty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17480","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/2502.17480/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":"2502.17480","created_at":"2026-07-05T10:19:11.432672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17480v1","created_at":"2026-07-05T10:19:11.432672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17480","created_at":"2026-07-05T10:19:11.432672+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6KEVUSPRDVB","created_at":"2026-07-05T10:19:11.432672+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6KEVUSPRDVBKIL2","created_at":"2026-07-05T10:19:11.432672+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6KEVUSP","created_at":"2026-07-05T10:19:11.432672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20696","citing_title":"MindAlign: Decoding Inner Speech from fMRI Signals via Multimodal Embedding Alignment under Limited Data","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09315","citing_title":"Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10688","citing_title":"DANCE: Detect and Classify Events in EEG","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08495","citing_title":"NeuralBench: A Unifying Framework to Benchmark NeuroAI Models","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ","json":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ.json","graph_json":"https://pith.science/api/pith-number/D6KEVUSPRDVBKIL2PI6QVAWCFJ/graph.json","events_json":"https://pith.science/api/pith-number/D6KEVUSPRDVBKIL2PI6QVAWCFJ/events.json","paper":"https://pith.science/paper/D6KEVUSP"},"agent_actions":{"view_html":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ","download_json":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ.json","view_paper":"https://pith.science/paper/D6KEVUSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17480&json=true","fetch_graph":"https://pith.science/api/pith-number/D6KEVUSPRDVBKIL2PI6QVAWCFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/D6KEVUSPRDVBKIL2PI6QVAWCFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ/action/storage_attestation","attest_author":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ/action/author_attestation","sign_citation":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ/action/citation_signature","submit_replication":"https://pith.science/pith/D6KEVUSPRDVBKIL2PI6QVAWCFJ/action/replication_record"}},"created_at":"2026-07-05T10:19:11.432672+00:00","updated_at":"2026-07-05T10:19:11.432672+00:00"}