{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T7KB5LNOBMFDJXCP5LHBWWEJRF","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":"5236764ad643d536d8a412ab63019ec23c85ed51786454568cfe70aebc7e54bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T08:18:02Z","title_canon_sha256":"d46eebca19136defbfdced467ab925624461f818819b360df52cda2dc35fe453"},"schema_version":"1.0","source":{"id":"2403.18926","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18926","created_at":"2026-07-05T08:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18926v2","created_at":"2026-07-05T08:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18926","created_at":"2026-07-05T08:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"T7KB5LNOBMFD","created_at":"2026-07-05T08:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"T7KB5LNOBMFDJXCP","created_at":"2026-07-05T08:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"T7KB5LNO","created_at":"2026-07-05T08:22:38Z"}],"graph_snapshots":[{"event_id":"sha256:92fe9cf52882f85713edfa2f9a6793c7f81aac8043ed41a922f9cc17a7f13603","target":"graph","created_at":"2026-07-05T08:22:38Z","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/2403.18926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are unnecessarily involved in computations via multiplying values by zero or low activation values. To address this issue, we present \\tool, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. \\tool leverages small experts and a threshold-based router to enable tokens to selectively engage only essential parameters. Our extensiv","authors_text":"Chaozheng Wang, Cuiyun Gao, Shiyi Qi, Wenchao Gu, Yuanhang Yang, Zenglin Xu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T08:18:02Z","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18926","kind":"arxiv","version":2},"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:e00aa3f3dd87afdbc5f6ce46300556e43d71a9d25e811bd5dd6938ee6686ac82","target":"record","created_at":"2026-07-05T08:22:38Z","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":"5236764ad643d536d8a412ab63019ec23c85ed51786454568cfe70aebc7e54bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T08:18:02Z","title_canon_sha256":"d46eebca19136defbfdced467ab925624461f818819b360df52cda2dc35fe453"},"schema_version":"1.0","source":{"id":"2403.18926","kind":"arxiv","version":2}},"canonical_sha256":"9fd41eadae0b0a34dc4feace1b5889896d3a7ffba40ccba21c48aa6992105ad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fd41eadae0b0a34dc4feace1b5889896d3a7ffba40ccba21c48aa6992105ad3","first_computed_at":"2026-07-05T08:22:38.962398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:38.962398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbUGxkBXH1uAcEoaF20jyKrQajQU2tYkpi1fcWxVFig6xWl6DbEDu0XWRK/3mEmo0vpkA+eGshzX3V66xjf0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:38.962943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18926","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00aa3f3dd87afdbc5f6ce46300556e43d71a9d25e811bd5dd6938ee6686ac82","sha256:92fe9cf52882f85713edfa2f9a6793c7f81aac8043ed41a922f9cc17a7f13603"],"state_sha256":"53bb34735914a26269be23a43d31aca42ddd9132ed1a13c9e2caf75b8d507f01"}