{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PWZJFKS5H54WFOTLR7BPMRXGOS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e5f815a0ec10f45c4c748ca0849fbca13846f2101c21b7a47c051e26bdf7c708","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-21T21:25:54Z","title_canon_sha256":"c121b2147897fb3756c9351b2dd1f12314a87174fb6eabc56739d505caac29cf"},"schema_version":"1.0","source":{"id":"2511.21740","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.21740","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2511.21740v5","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21740","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"PWZJFKS5H54W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PWZJFKS5H54WFOTL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PWZJFKS5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:411fb081d5368fa17c624cd90d453770dc69337e1c2e4d542a9b7e92bc08ccc8","target":"graph","created_at":"2026-05-17T23:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Integrated end-to-end with audio large language models and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The representations learned by the cross-species pretrained neural encoder transfer effectively and without major domain shift to human attempted and imagined speech recordings used in the Brain-to-Text benchmarks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A cross-species pretrained neural encoder combined with end-to-end training and audio LLMs reduces word error rate in neural speech decoding from 24.69% to 10.22% while aligning attempted and imagined speech."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A cross-species pretrained neural encoder enables end-to-end decoding of brain activity into sentences at 10.22 percent word error rate."}],"snapshot_sha256":"41767f63eea341d2f6ee2b0cd93a47a69053f83fc59f15f12d4c97f79098e62b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e952c07c7b922b9384a8363b223a8a6b4f3f67eff391543636779e235a365d04"},"paper":{"abstract_excerpt":"Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram language model (LM), preventing joint optimization of all stages simultaneously. Here, we introduce an end-to-end BraIn-to-Text (BIT) framework that translates neural activity into coherent sentences using a single differentiable neural network. Central to our approach is a cross-task, cross-species pretrained neural encoder, whose representations transfer to ","authors_text":"Chaofei Fan, Francis R Willett, Han Yu, Jingyuan Li, Lea Duncker, Liam Paninski, Linyang He, Nima Mesgarani, Scott Linderman, Tingkai Liu, Trung Le, Yizi Zhang","cross_cats":["cs.AI"],"headline":"A cross-species pretrained neural encoder enables end-to-end decoding of brain activity into sentences at 10.22 percent word error rate.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-21T21:25:54Z","title":"A cross-species neural foundation model for end-to-end speech decoding"},"references":{"count":25,"internal_anchors":8,"resolved_work":25,"sample":[{"cited_arxiv_id":"2407.10759","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen2-Audio Technical Report","work_id":"c249e63c-cf40-408f-a4ff-fdf68e8cbeb8","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Time-masked trans- formers with lightweight test-time adaptation for neural speech decoding.arXiv preprint arXiv:2507.02800,","work_id":"2391c167-698f-488d-9bc8-a6662d489b71","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Towards an end-to-end framework for invasive brain signal decoding with large language models.arXiv preprint arXiv:2406.11568,","work_id":"af8471c4-0b90-4b01-a172-e7abcdf7c548","year":null},{"cited_arxiv_id":"1904.09751","doi":"","is_internal_anchor":true,"ref_index":4,"title":"The Curious Case of Neural Text Degeneration","work_id":"1ef2ec4a-db7b-42b2-9416-0f1bb628c3c8","year":1904},{"cited_arxiv_id":"","doi":"10.1101/2022.04","is_internal_anchor":false,"ref_index":5,"title":"Stabilizing brain- computer interfaces through alignment of latent dynamics","work_id":"42f27d99-f1ac-42e6-8684-07beea8891c1","year":2022}],"snapshot_sha256":"84fa834ea3609f2b716136e5e4fe01ff8fd85c6636e61068642d51313a710e02"},"source":{"id":"2511.21740","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-17T19:56:23.299472Z","id":"fe5e8dba-2c17-4d88-b0fd-b585e708d394","model_set":{"reader":"grok-4.3"},"one_line_summary":"A cross-species pretrained neural encoder combined with end-to-end training and audio LLMs reduces word error rate in neural speech decoding from 24.69% to 10.22% while aligning attempted and imagined speech.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A cross-species pretrained neural encoder enables end-to-end decoding of brain activity into sentences at 10.22 percent word error rate.","strongest_claim":"Integrated end-to-end with audio large language models and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%.","weakest_assumption":"The representations learned by the cross-species pretrained neural encoder transfer effectively and without major domain shift to human attempted and imagined speech recordings used in the Brain-to-Text benchmarks."}},"verdict_id":"fe5e8dba-2c17-4d88-b0fd-b585e708d394"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7b90d911a2f5f30361d8f2cde2da2670c15ef05005062c640614ef1f47a90538","target":"record","created_at":"2026-05-17T23:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e5f815a0ec10f45c4c748ca0849fbca13846f2101c21b7a47c051e26bdf7c708","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-21T21:25:54Z","title_canon_sha256":"c121b2147897fb3756c9351b2dd1f12314a87174fb6eabc56739d505caac29cf"},"schema_version":"1.0","source":{"id":"2511.21740","kind":"arxiv","version":5}},"canonical_sha256":"7db292aa5d3f7962ba6b8fc2f646e674b070823c08611f0f0686311a49791fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7db292aa5d3f7962ba6b8fc2f646e674b070823c08611f0f0686311a49791fdd","first_computed_at":"2026-05-17T23:39:17.016781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:17.016781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hrtv6EokgmUhkAqtJb+nQZ31qbL+ZjTYCxwKlBGjQWb62HlMG4OE/+1YFKj0Cw3XCDmVzX1ihwI7emW+ZShACw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:17.017532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.21740","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b90d911a2f5f30361d8f2cde2da2670c15ef05005062c640614ef1f47a90538","sha256:411fb081d5368fa17c624cd90d453770dc69337e1c2e4d542a9b7e92bc08ccc8"],"state_sha256":"85e553bc339d541f254e548bd399fa2a9867c6bb6a5e660b26d76955efc0220c"}