{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I2CIDZGPFNHMRIZ2ZDVUJBDXYF","short_pith_number":"pith:I2CIDZGP","schema_version":"1.0","canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","source":{"kind":"arxiv","id":"2603.03312","version":3},"attestation_state":"computed","paper":{"title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values.","cross_cats":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Haonan Wang, Honglong Yang, Xiaomeng Li, Yuchen Wang, Yu Guo","submitted_at":"2026-02-09T02:47:07Z","abstract_excerpt":"Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental issues: Semantic Bias, where outputs collapse into generic linguistic templates; Signal Neglect, where models rely heavily on LLM priors to hallucinate fluent text even in the absence of meaningful signals; and the \"BLEU Trap\", where high-frequency stopwords inflate n-gram metrics, masking a lack of true semantic fidelity. To resolve these challenges, we move beyond conventional end-to-end pipelines and propose SemKey, a n"},"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":true},"canonical_record":{"source":{"id":"2603.03312","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-09T02:47:07Z","cross_cats_sorted":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"title_canon_sha256":"cf3bdb78697da02dc67bc8b5048b55de01a707da09f15456e384b2b1725e8982","abstract_canon_sha256":"f954f642bbc2f857ab5dbb58fa2c1e3f534d3d04a99bfd4583964bf4b5fc8cb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:44.560250Z","signature_b64":"QoP8Z1DER/bSMrJzd/OKLPZMbryfLUKmWyJfpHymCGHx/hlo5hfCO0i2bHfQahGaVFgKLHSlIa0Z/NTrDrmICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","last_reissued_at":"2026-06-02T01:03:44.559729Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:44.559729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values.","cross_cats":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Haonan Wang, Honglong Yang, Xiaomeng Li, Yuchen Wang, Yu Guo","submitted_at":"2026-02-09T02:47:07Z","abstract_excerpt":"Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental issues: Semantic Bias, where outputs collapse into generic linguistic templates; Signal Neglect, where models rely heavily on LLM priors to hallucinate fluent text even in the absence of meaningful signals; and the \"BLEU Trap\", where high-frequency stopwords inflate n-gram metrics, masking a lack of true semantic fidelity. To resolve these challenges, we move beyond conventional end-to-end pipelines and propose SemKey, a n"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our approach effectively eliminates hallucinations on noise inputs and achieves SOTA performance on these robust protocols","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That injecting semantic prompts as queries and EEG embeddings as key-value pairs will strictly force the LLM to ground generation in neural signals rather than linguistic priors","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SemKey decouples semantic objectives to ground EEG-to-text generation in neural signals, eliminating hallucinations on noise and improving results on retrieval accuracy and Fréchet distance metrics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bd259781417e141fd99254fc111a10802b95a808c568b1b582202ee9e9260f4d"},"source":{"id":"2603.03312","kind":"arxiv","version":3},"verdict":{"id":"c2f5201b-000f-4337-91da-23bca34ecc5a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:26:08.101828Z","strongest_claim":"our approach effectively eliminates hallucinations on noise inputs and achieves SOTA performance on these robust protocols","one_line_summary":"SemKey decouples semantic objectives to ground EEG-to-text generation in neural signals, eliminating hallucinations on noise and improving results on retrieval accuracy and Fréchet distance metrics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That injecting semantic prompts as queries and EEG embeddings as key-value pairs will strictly force the LLM to ground generation in neural signals rather than linguistic priors","pith_extraction_headline":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03312/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":2,"snapshot_sha256":"2447d0a90e864262fe38d76b61ef463c9120c07435075fbebae6bae0a60f9447"},"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":"2603.03312","created_at":"2026-06-02T01:03:44.559786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03312v3","created_at":"2026-06-02T01:03:44.559786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03312","created_at":"2026-06-02T01:03:44.559786+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2CIDZGPFNHM","created_at":"2026-06-02T01:03:44.559786+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2CIDZGPFNHMRIZ2","created_at":"2026-06-02T01:03:44.559786+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2CIDZGP","created_at":"2026-06-02T01:03:44.559786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF","json":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF.json","graph_json":"https://pith.science/api/pith-number/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/graph.json","events_json":"https://pith.science/api/pith-number/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/events.json","paper":"https://pith.science/paper/I2CIDZGP"},"agent_actions":{"view_html":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF","download_json":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF.json","view_paper":"https://pith.science/paper/I2CIDZGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03312&json=true","fetch_graph":"https://pith.science/api/pith-number/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/graph.json","fetch_events":"https://pith.science/api/pith-number/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/action/storage_attestation","attest_author":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/action/author_attestation","sign_citation":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/action/citation_signature","submit_replication":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/action/replication_record"}},"created_at":"2026-06-02T01:03:44.559786+00:00","updated_at":"2026-06-02T01:03:44.559786+00:00"}