{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NGO2HNS7N4Q7H5OT2ELS7U4ROX","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":"964b8f441eb13ca69a4f0a45b24d2cd16ad570100717c83acbbabce0aa7b5a82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T09:22:33Z","title_canon_sha256":"5df4b96521dc9dacf1345f1191d4c0ec79f18aa7dc740ce117346ea0ce542332"},"schema_version":"1.0","source":{"id":"2407.09816","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09816","created_at":"2026-07-05T09:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09816v4","created_at":"2026-07-05T09:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09816","created_at":"2026-07-05T09:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"NGO2HNS7N4Q7","created_at":"2026-07-05T09:00:38Z"},{"alias_kind":"pith_short_16","alias_value":"NGO2HNS7N4Q7H5OT","created_at":"2026-07-05T09:00:38Z"},{"alias_kind":"pith_short_8","alias_value":"NGO2HNS7","created_at":"2026-07-05T09:00:38Z"}],"graph_snapshots":[{"event_id":"sha256:c8dd7f6c0c2b4186c7eb94baa6f8c9fa839a3eb2189d05e636691ca96c42375e","target":"graph","created_at":"2026-07-05T09:00:38Z","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/2407.09816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or inference costs. In MoE, there is an important module called the router, which is used to distribute each token to the experts. Currently, the mainstream routing methods include dynamic routing and fixed routing. Despite their promising results, MoE models encounter several challenges. Primarily, for dynamic routing methods, the dispersion of training tokens acr","authors_text":"Guangyuan Ma, Guiguang Ding, Haoran Lian, Hui Chen, Songlin Hu, Wei Zhou, Xing Wu, Xue Bai, Yizhe Xiong, Zhenpeng Su, Zijia Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T09:22:33Z","title":"MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09816","kind":"arxiv","version":4},"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":"sha256:8fff98c930ac65dcd004a1bab7e94db459d8109789c4b90968337b92243044c3","target":"record","created_at":"2026-07-05T09:00:38Z","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":"964b8f441eb13ca69a4f0a45b24d2cd16ad570100717c83acbbabce0aa7b5a82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T09:22:33Z","title_canon_sha256":"5df4b96521dc9dacf1345f1191d4c0ec79f18aa7dc740ce117346ea0ce542332"},"schema_version":"1.0","source":{"id":"2407.09816","kind":"arxiv","version":4}},"canonical_sha256":"699da3b65f6f21f3f5d3d1172fd39175c0258c323345f0d2ca5d65e656ddf79b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"699da3b65f6f21f3f5d3d1172fd39175c0258c323345f0d2ca5d65e656ddf79b","first_computed_at":"2026-07-05T09:00:38.096341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:38.096341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uZj0oXfjs25xTk0SV6NniUZ4n0I/9tl6Q+0Nkq7FVVeamGw+Sf6xiXvWOvrI18rStGZkgX0wX1WkYjfC6LXnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:38.096763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09816","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fff98c930ac65dcd004a1bab7e94db459d8109789c4b90968337b92243044c3","sha256:c8dd7f6c0c2b4186c7eb94baa6f8c9fa839a3eb2189d05e636691ca96c42375e"],"state_sha256":"7c94e4bc365f366246d164ce37374fdddbdfd8ad491fe00f2f8becf4c1badc12"}