{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TPND2KRXWWBMNZWLSA4BQSGOUW","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":"7ab9bb5fc954833aa785acadcf4c5174efa374d51530ede7e8eb4c5523936d0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-12T21:26:56Z","title_canon_sha256":"875e46653347ae96c3042e82782e4869f44e64edd48dc0cab821a18024759912"},"schema_version":"1.0","source":{"id":"2504.09345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09345","created_at":"2026-07-05T10:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09345v1","created_at":"2026-07-05T10:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09345","created_at":"2026-07-05T10:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"TPND2KRXWWBM","created_at":"2026-07-05T10:48:35Z"},{"alias_kind":"pith_short_16","alias_value":"TPND2KRXWWBMNZWL","created_at":"2026-07-05T10:48:35Z"},{"alias_kind":"pith_short_8","alias_value":"TPND2KRX","created_at":"2026-07-05T10:48:35Z"}],"graph_snapshots":[{"event_id":"sha256:ccc7d6e55b228659d65fbe8df134e6146d0867c2dea71dee9bc4e6bb0cd8d253","target":"graph","created_at":"2026-07-05T10:48:35Z","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/2504.09345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes present deployment challenges in resource-constrained environments with limited GPU memory capacity, as GPU memory is often insufficient to accommodate the full set of model weights. Consequently, typical deployments rely on CPU-GPU hybrid execution: the GPU handles compute-intensive GEMM operations, while the CPU processes the relatively lightweight attention mec","authors_text":"Lin Ma, Nishil Talati, Yichao Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-12T21:26:56Z","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09345","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":"sha256:596cf45e072f79446c91b606f0ea51d1f4e35d18b227cafd93fcd70f38680c50","target":"record","created_at":"2026-07-05T10:48:35Z","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":"7ab9bb5fc954833aa785acadcf4c5174efa374d51530ede7e8eb4c5523936d0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-12T21:26:56Z","title_canon_sha256":"875e46653347ae96c3042e82782e4869f44e64edd48dc0cab821a18024759912"},"schema_version":"1.0","source":{"id":"2504.09345","kind":"arxiv","version":1}},"canonical_sha256":"9bda3d2a37b582c6e6cb90381848cea5a9530b7eb36f0a53568e8ba09662f4b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bda3d2a37b582c6e6cb90381848cea5a9530b7eb36f0a53568e8ba09662f4b6","first_computed_at":"2026-07-05T10:48:35.885191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:35.885191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"01C/gdQtHwfjWqVxh/yBOH0/emZxOO9StWQNsYJ18f2FxDXGQzcNi2xOqOjUyh2N+MTjs9+gkp1EYpbm4VM3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:35.885660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596cf45e072f79446c91b606f0ea51d1f4e35d18b227cafd93fcd70f38680c50","sha256:ccc7d6e55b228659d65fbe8df134e6146d0867c2dea71dee9bc4e6bb0cd8d253"],"state_sha256":"2793db7b4a34a883ce7717a30671a93e0e1548260e3e28ba55a7025fa80315d1"}