{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QNGSTCB4SHXTA45YQLRBCEDXTX","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":"5ae12556e0514fa1cd6f2332c397c1a81b25dea8d948ab5107aefddfe42f4d95","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T13:41:17Z","title_canon_sha256":"6ab409b9952329ffc9a732037540367b2b489d9145237c18e9978639c0a7950b"},"schema_version":"1.0","source":{"id":"2505.03531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03531","created_at":"2026-07-05T10:59:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03531v1","created_at":"2026-07-05T10:59:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03531","created_at":"2026-07-05T10:59:17Z"},{"alias_kind":"pith_short_12","alias_value":"QNGSTCB4SHXT","created_at":"2026-07-05T10:59:17Z"},{"alias_kind":"pith_short_16","alias_value":"QNGSTCB4SHXTA45Y","created_at":"2026-07-05T10:59:17Z"},{"alias_kind":"pith_short_8","alias_value":"QNGSTCB4","created_at":"2026-07-05T10:59:17Z"}],"graph_snapshots":[{"event_id":"sha256:8a183f8a48ceb0af21983bb9cd7dcc57147d7fd351fa58e76df624a61104901b","target":"graph","created_at":"2026-07-05T10:59:17Z","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/2505.03531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE architectures. With the emergence of DeepSeek Models, fine-grained MoE models are gaining popularity, yet research on them remains limited. Therefore, we want to discuss the efficiency dynamic under different service loads. Additionally, fine-grained models allow deployers to reduce the number of routed experts, both activated counts and total counts, raising the questi","authors_text":"Bo Du, Hai Zhao, Haoqi Yang, Luohe Shi, Mengjia Shen, Ping Wang, Qiwei Li, Zuchao Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T13:41:17Z","title":"Faster MoE LLM Inference for Extremely Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03531","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":"sha256:94b5c579948e10179b9cffece0131d61aabdf9a16d0f634574f69e88e25c9888","target":"record","created_at":"2026-07-05T10:59:17Z","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":"5ae12556e0514fa1cd6f2332c397c1a81b25dea8d948ab5107aefddfe42f4d95","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T13:41:17Z","title_canon_sha256":"6ab409b9952329ffc9a732037540367b2b489d9145237c18e9978639c0a7950b"},"schema_version":"1.0","source":{"id":"2505.03531","kind":"arxiv","version":1}},"canonical_sha256":"834d29883c91ef3073b882e21110779def093dd0da9c0a5d7755e82a92aa473d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"834d29883c91ef3073b882e21110779def093dd0da9c0a5d7755e82a92aa473d","first_computed_at":"2026-07-05T10:59:17.711457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:17.711457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhlFaXTVWJDBJgRnK3JMOF9/kQCWCsagI5n3T3SEh1Qszr7Tl3RHN5Giv4jRyZMklUdEHJE+UN6CHkLh/wkQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:17.711866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b5c579948e10179b9cffece0131d61aabdf9a16d0f634574f69e88e25c9888","sha256:8a183f8a48ceb0af21983bb9cd7dcc57147d7fd351fa58e76df624a61104901b"],"state_sha256":"9a476ff386d77ec3085d9944e8c0400933da3f73ad4722559a4f4ebbb7296113"}