{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I2CIDZGPFNHMRIZ2ZDVUJBDXYF","short_pith_number":"pith:I2CIDZGP","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"},"canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","source":{"kind":"arxiv","id":"2603.03312","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03312","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03312v3","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03312","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"I2CIDZGPFNHM","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"I2CIDZGPFNHMRIZ2","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"I2CIDZGP","created_at":"2026-06-02T01:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I2CIDZGPFNHMRIZ2ZDVUJBDXYF","target":"record","payload":{"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"},"canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","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"},"source_kind":"arxiv","source_id":"2603.03312","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"usZRCil/JWuwPNKbMi9XoXEFpPbuqWk3cGs/g7AoBLdd76pH5mDUawPiwgAacAQn/nAQCzWO4/CptKiuwMYNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:24:58.130932Z"},"content_sha256":"b497f3c15b1295ffd87c9529ce2fbf7d502c4413d37d9e9f84fc3e67307f9a76","schema_version":"1.0","event_id":"sha256:b497f3c15b1295ffd87c9529ce2fbf7d502c4413d37d9e9f84fc3e67307f9a76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I2CIDZGPFNHMRIZ2ZDVUJBDXYF","target":"graph","payload":{"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"},"verdict_id":"c2f5201b-000f-4337-91da-23bca34ecc5a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnX66SRgW7+jtlB+INxuqERZ63oKkEyN4LRh6Zjlgvif+fIfK9KfBCON0wfA2ynsklz0Ok+pHGkhtOEux8mpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:24:58.131682Z"},"content_sha256":"eb7b6bffa4a8f0b0c74dcb6e8ccd91fa277f1f7dbf4c407936d64950c1d8d838","schema_version":"1.0","event_id":"sha256:eb7b6bffa4a8f0b0c74dcb6e8ccd91fa277f1f7dbf4c407936d64950c1d8d838"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/bundle.json","state_url":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T12:24:58Z","links":{"resolver":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF","bundle":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/bundle.json","state":"https://pith.science/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2CIDZGPFNHMRIZ2ZDVUJBDXYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I2CIDZGPFNHMRIZ2ZDVUJBDXYF","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":"f954f642bbc2f857ab5dbb58fa2c1e3f534d3d04a99bfd4583964bf4b5fc8cb1","cross_cats_sorted":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-09T02:47:07Z","title_canon_sha256":"cf3bdb78697da02dc67bc8b5048b55de01a707da09f15456e384b2b1725e8982"},"schema_version":"1.0","source":{"id":"2603.03312","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03312","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03312v3","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03312","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"I2CIDZGPFNHM","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"I2CIDZGPFNHMRIZ2","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"I2CIDZGP","created_at":"2026-06-02T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:eb7b6bffa4a8f0b0c74dcb6e8ccd91fa277f1f7dbf4c407936d64950c1d8d838","target":"graph","created_at":"2026-06-02T01:03:44Z","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":"our approach effectively eliminates hallucinations on noise inputs and achieves SOTA performance on these robust protocols"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values."}],"snapshot_sha256":"bd259781417e141fd99254fc111a10802b95a808c568b1b582202ee9e9260f4d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2447d0a90e864262fe38d76b61ef463c9120c07435075fbebae6bae0a60f9447"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.03312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haonan Wang, Honglong Yang, Xiaomeng Li, Yuchen Wang, Yu Guo","cross_cats":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"headline":"SemKey grounds EEG-to-text output in neural signals by treating semantic prompts as queries and EEG embeddings as keys and values.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-09T02:47:07Z","title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03312","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T06:26:08.101828Z","id":"c2f5201b-000f-4337-91da-23bca34ecc5a","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"our approach effectively eliminates hallucinations on noise inputs and achieves SOTA performance on these robust protocols","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"}},"verdict_id":"c2f5201b-000f-4337-91da-23bca34ecc5a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b497f3c15b1295ffd87c9529ce2fbf7d502c4413d37d9e9f84fc3e67307f9a76","target":"record","created_at":"2026-06-02T01:03:44Z","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":"f954f642bbc2f857ab5dbb58fa2c1e3f534d3d04a99bfd4583964bf4b5fc8cb1","cross_cats_sorted":["cs.AI","cs.HC","eess.AS","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-09T02:47:07Z","title_canon_sha256":"cf3bdb78697da02dc67bc8b5048b55de01a707da09f15456e384b2b1725e8982"},"schema_version":"1.0","source":{"id":"2603.03312","kind":"arxiv","version":3}},"canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468481e4cf2b4ec8a33ac8eb448477c1587aa42a141430bd3f30a0bc07aa0a06","first_computed_at":"2026-06-02T01:03:44.559729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:44.559729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QoP8Z1DER/bSMrJzd/OKLPZMbryfLUKmWyJfpHymCGHx/hlo5hfCO0i2bHfQahGaVFgKLHSlIa0Z/NTrDrmICQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:44.560250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03312","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b497f3c15b1295ffd87c9529ce2fbf7d502c4413d37d9e9f84fc3e67307f9a76","sha256:eb7b6bffa4a8f0b0c74dcb6e8ccd91fa277f1f7dbf4c407936d64950c1d8d838"],"state_sha256":"db5d43ade0923a5eb49ab73d3e346a9bb9acd4c0e19f01b6c791aaf19a12a974"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2mqDwFs14xvbJk4wwqURqrpDF3AfV6m3KK6qJuA8YveUXhJPNflaPwCjACsKhjhXZXkpQ7NQPjDRvCZXdfcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:24:58.136919Z","bundle_sha256":"de5663b2ac0fea4107e36c4a00d91eb780a45fd9e9ac5ca577c6d65fde3dc41a"}}