{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GAIYONA27QJZ5WZRI3A54XH5KW","short_pith_number":"pith:GAIYONA2","schema_version":"1.0","canonical_sha256":"301187341afc139edb3146c1de5cfd559fabbcbc7617d1fb69e5b6e30d1b9e42","source":{"kind":"arxiv","id":"2605.10933","version":3},"attestation_state":"computed","paper":{"title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DECO sparse MoE matches dense Transformer performance while activating only 20% of experts.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chaojun Xiao, Chenyang Song, Weilin Zhao, Xu Han, Yingfa Chen, Zhiyuan Liu","submitted_at":"2026-05-11T17:58:28Z","abstract_excerpt":"While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-access bottlenecks, which hinder efficient end-side deployment that simultaneously requires high performance, low computational cost, and small storage overhead. To achieve these properties, we present DECO, a sparse MoE architecture designed to match the performance of dense Transformers under identical total parameter budgets and training tokens. DECO utilizes the differentiable and flexible ReLU-based routing enhance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.10933","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T17:58:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f02b018379c25ddd549c16fb7d757a3ba9e8fb0b63074a6bad757b66cc6e9974","abstract_canon_sha256":"132fa94163a8ca5817b3b05d10ac9448834d853755a9e12f470929fab39dc91a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:05.289148Z","signature_b64":"KfnrNMTwO0PUNkImjYosp5QCOvoyaLrMhkWbOoAQFECdep9edp9s42QHHjePm1+sefpTJZm5emZE2Jse6MbsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"301187341afc139edb3146c1de5cfd559fabbcbc7617d1fb69e5b6e30d1b9e42","last_reissued_at":"2026-05-21T02:05:05.288209Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:05.288209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DECO sparse MoE matches dense Transformer performance while activating only 20% of experts.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chaojun Xiao, Chenyang Song, Weilin Zhao, Xu Han, Yingfa Chen, Zhiyuan Liu","submitted_at":"2026-05-11T17:58:28Z","abstract_excerpt":"While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-access bottlenecks, which hinder efficient end-side deployment that simultaneously requires high performance, low computational cost, and small storage overhead. To achieve these properties, we present DECO, a sparse MoE architecture designed to match the performance of dense Transformers under identical total parameter budgets and training tokens. DECO utilizes the differentiable and flexible ReLU-based routing enhance"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DECO, activating only 20% of experts, matches dense performance and outperforms established MoE baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learned expert-wise scaling and NormSiLU will continue to produce stable sparsity and matching performance when model size, data distribution, or hardware change substantially.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DECO matches dense model performance at 20% expert activation via ReLU-based routing with learnable scaling and the NormSiLU activation, plus a 3x real-hardware speedup.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DECO sparse MoE matches dense Transformer performance while activating only 20% of experts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fb0d46a45ae445bdec59bbd573a2ac45d8e9b9807b9a5e97c2abb680d0d9a919"},"source":{"id":"2605.10933","kind":"arxiv","version":3},"verdict":{"id":"b57856c1-ac6a-44b7-9016-87aeeeded385","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:25:41.711109Z","strongest_claim":"DECO, activating only 20% of experts, matches dense performance and outperforms established MoE baselines.","one_line_summary":"DECO matches dense model performance at 20% expert activation via ReLU-based routing with learnable scaling and the NormSiLU activation, plus a 3x real-hardware speedup.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learned expert-wise scaling and NormSiLU will continue to produce stable sparsity and matching performance when model size, data distribution, or hardware change substantially.","pith_extraction_headline":"DECO sparse MoE matches dense Transformer performance while activating only 20% of experts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10933/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:02:00.913621Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:36:55.079203Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:17.132399Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:53:45.739118Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"96fadb87ebbca95e4bdf70d6c14a464c9c1764e752eea7a100432d28aacfb521"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b3f92bf15c7f14242316b7185ec75741ceb26ba35c9d21eee0ef878cf7d36495"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.10933","created_at":"2026-05-21T02:05:05.288326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10933v3","created_at":"2026-05-21T02:05:05.288326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10933","created_at":"2026-05-21T02:05:05.288326+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAIYONA27QJZ","created_at":"2026-05-21T02:05:05.288326+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAIYONA27QJZ5WZR","created_at":"2026-05-21T02:05:05.288326+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAIYONA2","created_at":"2026-05-21T02:05:05.288326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW","json":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW.json","graph_json":"https://pith.science/api/pith-number/GAIYONA27QJZ5WZRI3A54XH5KW/graph.json","events_json":"https://pith.science/api/pith-number/GAIYONA27QJZ5WZRI3A54XH5KW/events.json","paper":"https://pith.science/paper/GAIYONA2"},"agent_actions":{"view_html":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW","download_json":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW.json","view_paper":"https://pith.science/paper/GAIYONA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10933&json=true","fetch_graph":"https://pith.science/api/pith-number/GAIYONA27QJZ5WZRI3A54XH5KW/graph.json","fetch_events":"https://pith.science/api/pith-number/GAIYONA27QJZ5WZRI3A54XH5KW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW/action/storage_attestation","attest_author":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW/action/author_attestation","sign_citation":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW/action/citation_signature","submit_replication":"https://pith.science/pith/GAIYONA27QJZ5WZRI3A54XH5KW/action/replication_record"}},"created_at":"2026-05-21T02:05:05.288326+00:00","updated_at":"2026-05-21T02:05:05.288326+00:00"}