{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YW23VQT665DLL7ZLISFS6AXWQJ","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":"6f65849a815df0dbc2f8416109dc1dc16ee726dcee426e450418446feb9cc78b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T14:58:52Z","title_canon_sha256":"248778a827c56431924e891224cb4f7c296ede1244889e236e056b1828e0b0b3"},"schema_version":"1.0","source":{"id":"2606.00761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00761","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00761v1","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00761","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"YW23VQT665DL","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"YW23VQT665DLL7ZL","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"YW23VQT6","created_at":"2026-06-02T01:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:64277bc6c5f953b15003a36036135b9f522c136d4d52b293183e845a5ae58e85","target":"graph","created_at":"2026-06-02T01:04:04Z","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/2606.00761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating function -- is typically fixed throughout training. In this work, we propose Confidence-Aware SwiGLU ($\\kappa$-SwiGLU), a variant of SwiGLU for Mixture-of-Experts (MoE) models that adjusts expert gate sharpness according to token-level routing confidence. Specifically, $\\kappa$-SwiGLU parameterizes the SiLU gate sharpness coefficient as a learnable function of the router logit, enabling each expert gate unit to interpolate between smooth, broadly acti","authors_text":"Liangli Zhen, Rick Siow Mong Goh, Shaohua Li, Xiaobing Sun, Xiuchao Sui, Yong Liu, Yuhang Wu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T14:58:52Z","title":"Confidence-Adaptive SwiGLU for Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00761","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":"sha256:032040c84d527db75254af39a28d62825b84c92739aa4af6b192496b4906dbb8","target":"record","created_at":"2026-06-02T01:04:04Z","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":"6f65849a815df0dbc2f8416109dc1dc16ee726dcee426e450418446feb9cc78b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T14:58:52Z","title_canon_sha256":"248778a827c56431924e891224cb4f7c296ede1244889e236e056b1828e0b0b3"},"schema_version":"1.0","source":{"id":"2606.00761","kind":"arxiv","version":1}},"canonical_sha256":"c5b5bac27ef746b5ff2b448b2f02f6824102b46b987b773a822ee8c80bd65fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5b5bac27ef746b5ff2b448b2f02f6824102b46b987b773a822ee8c80bd65fba","first_computed_at":"2026-06-02T01:04:04.990623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:04.990623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"meBjMrt05PrmJrulv5GYaSZlzbFf2wcaq3Bn1yndZ8dB60RqhYOGpgoGHtfp2ZO0KbGphDXoJL9LR3PiuIBzCw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:04.990993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:032040c84d527db75254af39a28d62825b84c92739aa4af6b192496b4906dbb8","sha256:64277bc6c5f953b15003a36036135b9f522c136d4d52b293183e845a5ae58e85"],"state_sha256":"e94631f887f9312053e5e8681472c8d3976906ed402c49b89e9de7a57ed4c8a7"}