{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DI2TYUIYCACW5JHFI4F5PICNXO","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":"8faaa6447b1b4fed03cefa7200c26fc2cc39b4509c2065fe6eba0a2c0c454907","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:50:06Z","title_canon_sha256":"dd484a584f5a27d52283f01bed43fc6a74be2bd45b1f39d390e4aa4ef0f36642"},"schema_version":"1.0","source":{"id":"2605.20749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20749","created_at":"2026-05-21T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20749v1","created_at":"2026-05-21T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20749","created_at":"2026-05-21T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"DI2TYUIYCACW","created_at":"2026-05-21T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"DI2TYUIYCACW5JHF","created_at":"2026-05-21T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"DI2TYUIY","created_at":"2026-05-21T01:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:f41cb409bfafc1b9904de8d751f9f6a5f436758004fc01a49f1636006b2c3112","target":"graph","created_at":"2026-05-21T01:04:52Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.20749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, yet the underlying reasons for this advantage remain unclear. In this work, we study GLU by analyzing two-layer networks in the neural tangent kernel (NTK) regime. Our analysis reveals that the GLU structure reshapes the NTK spectrum, leading to a smaller condition number and a more compact eigenvalue distribution. Building on this finding, we further analyze the resulting training dynamics and show how the reshaped sp","authors_text":"Peisong Wen, Qianqian Xu, Qingming Huang, Xingyu Lyu, Zhiyong Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:50:06Z","title":"The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20749","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55601e51186ac53677429acbca4c9d2245e10e7a3a95d78a0f3d1b5018780aec","target":"record","created_at":"2026-05-21T01:04:52Z","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":"8faaa6447b1b4fed03cefa7200c26fc2cc39b4509c2065fe6eba0a2c0c454907","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:50:06Z","title_canon_sha256":"dd484a584f5a27d52283f01bed43fc6a74be2bd45b1f39d390e4aa4ef0f36642"},"schema_version":"1.0","source":{"id":"2605.20749","kind":"arxiv","version":1}},"canonical_sha256":"1a353c511810056ea4e5470bd7a04dbbaf0b96020a5b7db956b7e713bc41217b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a353c511810056ea4e5470bd7a04dbbaf0b96020a5b7db956b7e713bc41217b","first_computed_at":"2026-05-21T01:04:52.162056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:52.162056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TSAP6djZ55BUnTUq8tH8KEJKw/57AVu59myJyoGHTDqW6FTSS094f+/By+nfxQXxIA/WbFuL1Frttx3jGKNYAg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:52.162902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55601e51186ac53677429acbca4c9d2245e10e7a3a95d78a0f3d1b5018780aec","sha256:f41cb409bfafc1b9904de8d751f9f6a5f436758004fc01a49f1636006b2c3112"],"state_sha256":"9c319bdd140d004f410aa41cbeddadf8469a8c4486e832804450534ecf6a8550"}