{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S63VMP73RLD6XIO245LVCMWGRV","short_pith_number":"pith:S63VMP73","schema_version":"1.0","canonical_sha256":"97b7563ffb8ac7eba1dae7575132c68d72d78ca5010ed1faf7b9d1fdfe36aa20","source":{"kind":"arxiv","id":"2506.02098","version":1},"attestation_state":"computed","paper":{"title":"LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dulhan Jayalath, Francesco Mantegna, Gereon Elvers, Gilad Landau, Mark Woolrich, Miran \\\"Ozdogan, Oiwi Parker Jones, Pratik Somaiya","submitted_at":"2025-06-02T17:59:41Z","abstract_excerpt":"LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5$\\times$ larger than the next comparable dataset and 50$\\times$ larger than most. This unprecedented `depth' of within-subject data enables exploration of neural representations at a scale previously unavailable with non-invasive methods. LibriBrain comprises high-quality MEG recordings together with detailed annotations from a single participant listening to naturalistic spoken English, covering nearly the full Sherlock Holmes canon. Designed to support advances in ne"},"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":"2506.02098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"a525b65f67d13a903b509bc856b5ae6e4fd934217d1fc1f84ce9693e241bd95e","abstract_canon_sha256":"d3f8182d3950e0ea100e88809b76303e6d47510bf19112a12dacefa8d6205699"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:32.386087Z","signature_b64":"IJhr6UyoTbSc2quSAED0Z1FByjbu07iiOIlvXXVgAvlF6Y7zLLYbziC6LOXvXDQ/0hat5ZOtnfp96XvcCLzZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b7563ffb8ac7eba1dae7575132c68d72d78ca5010ed1faf7b9d1fdfe36aa20","last_reissued_at":"2026-07-05T11:14:32.385664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:32.385664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dulhan Jayalath, Francesco Mantegna, Gereon Elvers, Gilad Landau, Mark Woolrich, Miran \\\"Ozdogan, Oiwi Parker Jones, Pratik Somaiya","submitted_at":"2025-06-02T17:59:41Z","abstract_excerpt":"LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5$\\times$ larger than the next comparable dataset and 50$\\times$ larger than most. This unprecedented `depth' of within-subject data enables exploration of neural representations at a scale previously unavailable with non-invasive methods. LibriBrain comprises high-quality MEG recordings together with detailed annotations from a single participant listening to naturalistic spoken English, covering nearly the full Sherlock Holmes canon. Designed to support advances in ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02098","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/2506.02098/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":"2506.02098","created_at":"2026-07-05T11:14:32.385721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02098v1","created_at":"2026-07-05T11:14:32.385721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02098","created_at":"2026-07-05T11:14:32.385721+00:00"},{"alias_kind":"pith_short_12","alias_value":"S63VMP73RLD6","created_at":"2026-07-05T11:14:32.385721+00:00"},{"alias_kind":"pith_short_16","alias_value":"S63VMP73RLD6XIO2","created_at":"2026-07-05T11:14:32.385721+00:00"},{"alias_kind":"pith_short_8","alias_value":"S63VMP73","created_at":"2026-07-05T11:14:32.385721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31173","citing_title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13099","citing_title":"Bypassing Direct Reconstruction: Speech Detection from MEG via Large-Scale Audio Retrieval","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08075","citing_title":"Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV","json":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV.json","graph_json":"https://pith.science/api/pith-number/S63VMP73RLD6XIO245LVCMWGRV/graph.json","events_json":"https://pith.science/api/pith-number/S63VMP73RLD6XIO245LVCMWGRV/events.json","paper":"https://pith.science/paper/S63VMP73"},"agent_actions":{"view_html":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV","download_json":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV.json","view_paper":"https://pith.science/paper/S63VMP73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02098&json=true","fetch_graph":"https://pith.science/api/pith-number/S63VMP73RLD6XIO245LVCMWGRV/graph.json","fetch_events":"https://pith.science/api/pith-number/S63VMP73RLD6XIO245LVCMWGRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV/action/storage_attestation","attest_author":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV/action/author_attestation","sign_citation":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV/action/citation_signature","submit_replication":"https://pith.science/pith/S63VMP73RLD6XIO245LVCMWGRV/action/replication_record"}},"created_at":"2026-07-05T11:14:32.385721+00:00","updated_at":"2026-07-05T11:14:32.385721+00:00"}