{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TL74742EQJSVLWHVCPTHIG5UNN","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":"1eaec1fc3e699702c70785e807ffec57aec6346492581f051d9353d3dd7adad8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T08:18:30Z","title_canon_sha256":"f96c852ed78bdab83e740c6791be8f797e7cbfb8953e6b3c45b26419e648e9be"},"schema_version":"1.0","source":{"id":"2405.14297","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14297","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14297v4","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14297","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"TL74742EQJSV","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"TL74742EQJSVLWHV","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"TL74742E","created_at":"2026-07-05T10:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:5cf971bd9da521d34a5473b012b22a8af0b248adef863df600cf033139912638","target":"graph","created_at":"2026-07-05T10:27:10Z","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/2405.14297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising results.However, the performance of SMoE heavily depends on the choice of hyper-parameters, such as the number of experts and the number of experts to be activated (referred to as top-k), resulting in significant computational overhead due to the extensive model training by searching over various hyper-parameter configurations. As a remedy, we introduce the Dynamic Mixture of Experts (DynMoE) technique. DynMoE incorporat","authors_text":"Tao Lin, Xiaoying Tang, Yongxin Guo, Zhaopeng Tu, Zhenglin Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T08:18:30Z","title":"Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14297","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":"sha256:071eaee1755ceea0cc8d0749705dfbeec14850dad220c9c22c3e486e4e298f3f","target":"record","created_at":"2026-07-05T10:27:10Z","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":"1eaec1fc3e699702c70785e807ffec57aec6346492581f051d9353d3dd7adad8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T08:18:30Z","title_canon_sha256":"f96c852ed78bdab83e740c6791be8f797e7cbfb8953e6b3c45b26419e648e9be"},"schema_version":"1.0","source":{"id":"2405.14297","kind":"arxiv","version":4}},"canonical_sha256":"9affcff344826555d8f513e6741bb46b775a5e16024868831a21a954fbdf18ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9affcff344826555d8f513e6741bb46b775a5e16024868831a21a954fbdf18ed","first_computed_at":"2026-07-05T10:27:10.194261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:10.194261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5dZO9MSJas6l86U1ZzDt8lBassL4mTfFt8ChAexGiqAKNXO/9GyCQDpqFHfd9G6xAM2zsIdYiMv68PBiLx/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:10.194878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14297","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:071eaee1755ceea0cc8d0749705dfbeec14850dad220c9c22c3e486e4e298f3f","sha256:5cf971bd9da521d34a5473b012b22a8af0b248adef863df600cf033139912638"],"state_sha256":"69ff925987335ff1f7e09259bab758c59fde07c9eed49bc4aa284d1120a4add8"}