{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JPLYJKA4KGZW7G4LHG32ABABMF","short_pith_number":"pith:JPLYJKA4","canonical_record":{"source":{"id":"2604.12579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T11:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"9af270117c5899c81d5a7cff4e6ece4dbccbf0bb23d3a8e9175f2e6483a1aa0f","abstract_canon_sha256":"646f6c7133462083e17a4d8a349f9d85760e78bd1a2d289fe4b2504f5b74175c"},"schema_version":"1.0"},"canonical_sha256":"4bd784a81c51b36f9b8b39b7a00401617fc848a563fe510bb1a36f0e6e3174ac","source":{"kind":"arxiv","id":"2604.12579","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12579","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12579v3","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12579","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"JPLYJKA4KGZW","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"JPLYJKA4KGZW7G4L","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"JPLYJKA4","created_at":"2026-06-01T01:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JPLYJKA4KGZW7G4LHG32ABABMF","target":"record","payload":{"canonical_record":{"source":{"id":"2604.12579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T11:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"9af270117c5899c81d5a7cff4e6ece4dbccbf0bb23d3a8e9175f2e6483a1aa0f","abstract_canon_sha256":"646f6c7133462083e17a4d8a349f9d85760e78bd1a2d289fe4b2504f5b74175c"},"schema_version":"1.0"},"canonical_sha256":"4bd784a81c51b36f9b8b39b7a00401617fc848a563fe510bb1a36f0e6e3174ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:39.638251Z","signature_b64":"amrq7yVOiFwu9vGPzNzl3LJQLaqUod7WeCjSjtvlPTGEJdfDYPFZw6LurNK3T2Hw7OrXAID6nb85tAxTdjsWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd784a81c51b36f9b8b39b7a00401617fc848a563fe510bb1a36f0e6e3174ac","last_reissued_at":"2026-06-01T01:02:39.637363Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:39.637363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.12579","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":"2026-06-01T01:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BU+cWCowmRjJsuQHPM2Rd3Z1XqiLGgkmwyoJ2ORQQK3+1TcX2NQJ9ojSYaYzbja4tZXWHwiGaUf9hK1N7QiKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T05:58:38.790717Z"},"content_sha256":"8687ddd33adb3e35b2a6be215c6d18c43f90c4a032c47493c1dea9f38555fdc5","schema_version":"1.0","event_id":"sha256:8687ddd33adb3e35b2a6be215c6d18c43f90c4a032c47493c1dea9f38555fdc5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JPLYJKA4KGZW7G4LHG32ABABMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cuntai Guan, Guanxiang Huang, Motoaki Kawanabe, Qibin Zhao, Runhe Zhou, Shanglin Li, Xinliang Zhou, Yi Ding","submitted_at":"2026-04-14T11:03:51Z","abstract_excerpt":"Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EEG-based paradigms, one promising approach is to leverage their hierarchical structures, as recent studies have shown that both EEG and associated modalities (e.g., facial expressions) exhibit hierarchical structures reflecting complex cognitive processes. However, Euclidean embeddings struggle to re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework, assigns each modality to an expert in a learnable-curvature hyperbolic space and uses curvature-aware fusion to achieve state-of-the-art performance on benchmark datasets for emotion recognition, sleep staging, and cognitive assessment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That EEG and associated modalities exhibit hierarchical structures best captured by hyperbolic geometry with independently learnable curvatures per modality, and that the curvature-aware fusion strategy reliably emphasizes modalities with richer hierarchical information without introducing instability or overfitting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EEG-MoCE assigns each modality to a learnable-curvature hyperbolic expert and applies curvature-aware fusion to achieve state-of-the-art results on emotion recognition, sleep staging, and cognitive assessment benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2bd8367d58cea8f762876a95702c1398072035fa0b627c25a8e76cdaed6f6973"},"source":{"id":"2604.12579","kind":"arxiv","version":3},"verdict":{"id":"f971aecc-6792-4959-81ee-c47f72083dd4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T00:51:32.867093Z","strongest_claim":"EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework, assigns each modality to an expert in a learnable-curvature hyperbolic space and uses curvature-aware fusion to achieve state-of-the-art performance on benchmark datasets for emotion recognition, sleep staging, and cognitive assessment.","one_line_summary":"EEG-MoCE assigns each modality to a learnable-curvature hyperbolic expert and applies curvature-aware fusion to achieve state-of-the-art results on emotion recognition, sleep staging, and cognitive assessment benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That EEG and associated modalities exhibit hierarchical structures best captured by hyperbolic geometry with independently learnable curvatures per modality, and that the curvature-aware fusion strategy reliably emphasizes modalities with richer hierarchical information without introducing instability or overfitting.","pith_extraction_headline":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12579/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":"a6432c1bac3e266edbf9e5854a22e13660593a45c2c29089e4f4289d2f00b513"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f971aecc-6792-4959-81ee-c47f72083dd4"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksnQKCTHGTXcckhAICWyLyNe614NYOhaB3co+mbCalWr1Nn+RGrceFf+c2LzzepAtQ/zIlHRV/7q6joJydY4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T05:58:38.791183Z"},"content_sha256":"4281dce8a2a246839a5f13a21522eaa022a710a61210af44bcb638819bf57cb3","schema_version":"1.0","event_id":"sha256:4281dce8a2a246839a5f13a21522eaa022a710a61210af44bcb638819bf57cb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPLYJKA4KGZW7G4LHG32ABABMF/bundle.json","state_url":"https://pith.science/pith/JPLYJKA4KGZW7G4LHG32ABABMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPLYJKA4KGZW7G4LHG32ABABMF/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":"2026-06-20T05:58:38Z","links":{"resolver":"https://pith.science/pith/JPLYJKA4KGZW7G4LHG32ABABMF","bundle":"https://pith.science/pith/JPLYJKA4KGZW7G4LHG32ABABMF/bundle.json","state":"https://pith.science/pith/JPLYJKA4KGZW7G4LHG32ABABMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPLYJKA4KGZW7G4LHG32ABABMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JPLYJKA4KGZW7G4LHG32ABABMF","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":"646f6c7133462083e17a4d8a349f9d85760e78bd1a2d289fe4b2504f5b74175c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T11:03:51Z","title_canon_sha256":"9af270117c5899c81d5a7cff4e6ece4dbccbf0bb23d3a8e9175f2e6483a1aa0f"},"schema_version":"1.0","source":{"id":"2604.12579","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12579","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12579v3","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12579","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"JPLYJKA4KGZW","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"JPLYJKA4KGZW7G4L","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"JPLYJKA4","created_at":"2026-06-01T01:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:4281dce8a2a246839a5f13a21522eaa022a710a61210af44bcb638819bf57cb3","target":"graph","created_at":"2026-06-01T01:02:39Z","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":"EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework, assigns each modality to an expert in a learnable-curvature hyperbolic space and uses curvature-aware fusion to achieve state-of-the-art performance on benchmark datasets for emotion recognition, sleep staging, and cognitive assessment."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That EEG and associated modalities exhibit hierarchical structures best captured by hyperbolic geometry with independently learnable curvatures per modality, and that the curvature-aware fusion strategy reliably emphasizes modalities with richer hierarchical information without introducing instability or overfitting."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EEG-MoCE assigns each modality to a learnable-curvature hyperbolic expert and applies curvature-aware fusion to achieve state-of-the-art results on emotion recognition, sleep staging, and cognitive assessment benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals."}],"snapshot_sha256":"2bd8367d58cea8f762876a95702c1398072035fa0b627c25a8e76cdaed6f6973"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a6432c1bac3e266edbf9e5854a22e13660593a45c2c29089e4f4289d2f00b513"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.12579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EEG-based paradigms, one promising approach is to leverage their hierarchical structures, as recent studies have shown that both EEG and associated modalities (e.g., facial expressions) exhibit hierarchical structures reflecting complex cognitive processes. However, Euclidean embeddings struggle to re","authors_text":"Cuntai Guan, Guanxiang Huang, Motoaki Kawanabe, Qibin Zhao, Runhe Zhou, Shanglin Li, Xinliang Zhou, Yi Ding","cross_cats":[],"headline":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T11:03:51Z","title":"EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.12579","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-12T00:51:32.867093Z","id":"f971aecc-6792-4959-81ee-c47f72083dd4","model_set":{"reader":"grok-4.3"},"one_line_summary":"EEG-MoCE assigns each modality to a learnable-curvature hyperbolic expert and applies curvature-aware fusion to achieve state-of-the-art results on emotion recognition, sleep staging, and cognitive assessment benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals.","strongest_claim":"EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework, assigns each modality to an expert in a learnable-curvature hyperbolic space and uses curvature-aware fusion to achieve state-of-the-art performance on benchmark datasets for emotion recognition, sleep staging, and cognitive assessment.","weakest_assumption":"That EEG and associated modalities exhibit hierarchical structures best captured by hyperbolic geometry with independently learnable curvatures per modality, and that the curvature-aware fusion strategy reliably emphasizes modalities with richer hierarchical information without introducing instability or overfitting."}},"verdict_id":"f971aecc-6792-4959-81ee-c47f72083dd4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8687ddd33adb3e35b2a6be215c6d18c43f90c4a032c47493c1dea9f38555fdc5","target":"record","created_at":"2026-06-01T01:02:39Z","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":"646f6c7133462083e17a4d8a349f9d85760e78bd1a2d289fe4b2504f5b74175c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T11:03:51Z","title_canon_sha256":"9af270117c5899c81d5a7cff4e6ece4dbccbf0bb23d3a8e9175f2e6483a1aa0f"},"schema_version":"1.0","source":{"id":"2604.12579","kind":"arxiv","version":3}},"canonical_sha256":"4bd784a81c51b36f9b8b39b7a00401617fc848a563fe510bb1a36f0e6e3174ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bd784a81c51b36f9b8b39b7a00401617fc848a563fe510bb1a36f0e6e3174ac","first_computed_at":"2026-06-01T01:02:39.637363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:39.637363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amrq7yVOiFwu9vGPzNzl3LJQLaqUod7WeCjSjtvlPTGEJdfDYPFZw6LurNK3T2Hw7OrXAID6nb85tAxTdjsWBg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:39.638251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.12579","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8687ddd33adb3e35b2a6be215c6d18c43f90c4a032c47493c1dea9f38555fdc5","sha256:4281dce8a2a246839a5f13a21522eaa022a710a61210af44bcb638819bf57cb3"],"state_sha256":"9759729f327933aa7d51586f6a803654b9a577928a0cc857ba89acc9c01cf836"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cvxBt2LSIQsk4eftmaQYjsTnvOKwnxgbILI51B7k5eN6lRBGnI51RSFTGOccF5PLfOtt4cgk7M3XqM5VJALLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T05:58:38.793500Z","bundle_sha256":"536b6fdee653a900fe1dbd2cea21b763111660e27ef71640663dcd1ef1f9a707"}}