{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5ODLSPPQG4H5RXUM2DHQHLMOAR","short_pith_number":"pith:5ODLSPPQ","schema_version":"1.0","canonical_sha256":"eb86b93df0370fd8de8cd0cf03ad8e044639824c9851bd4220f975e4740ae91c","source":{"kind":"arxiv","id":"2608.07911","version":1},"attestation_state":"computed","paper":{"title":"When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Yu Zhang","submitted_at":"2026-08-08T04:29:20Z","abstract_excerpt":"Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard. This makes expert cache management an attractive lever: a policy that raised the hit rate would cut expert traffic per token. Evaluating that is a measurement problem, and we find the measurement fragile.\n  With a trace-driven, event-atomic simulator over three MoE models (40, 64, 128 experts), we isolate three evaluation axes that change conclusions, not just numbers. Replay semantics: under a fused-event traffic contract, an inconsistent per-access replay inflates r"},"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":false},"canonical_record":{"source":{"id":"2608.07911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T04:29:20Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"bf3a524c3128103bacec315e2f2aea127d53d7db696c153772c4a1a3b90bb540","abstract_canon_sha256":"751ee879a49714edb66b3d1c3ad3de9151a33647416ef1fc463fc168a012df50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:18:54.415032Z","signature_b64":"Q8KF87e4GHVaIHU7vZR0h9MRU8F7QdqG58goO4vCOLIh79uUfNvhm15FmLE6Oinxb307gbqYMVhfSki5d2jiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb86b93df0370fd8de8cd0cf03ad8e044639824c9851bd4220f975e4740ae91c","last_reissued_at":"2026-08-11T01:18:54.412694Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:18:54.412694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Yu Zhang","submitted_at":"2026-08-08T04:29:20Z","abstract_excerpt":"Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard. This makes expert cache management an attractive lever: a policy that raised the hit rate would cut expert traffic per token. Evaluating that is a measurement problem, and we find the measurement fragile.\n  With a trace-driven, event-atomic simulator over three MoE models (40, 64, 128 experts), we isolate three evaluation axes that change conclusions, not just numbers. Replay semantics: under a fused-event traffic contract, an inconsistent per-access replay inflates r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07911","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.07911/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2608.07911","created_at":"2026-08-11T01:18:54.413334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07911v1","created_at":"2026-08-11T01:18:54.413334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07911","created_at":"2026-08-11T01:18:54.413334+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ODLSPPQG4H5","created_at":"2026-08-11T01:18:54.413334+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ODLSPPQG4H5RXUM","created_at":"2026-08-11T01:18:54.413334+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ODLSPPQ","created_at":"2026-08-11T01:18:54.413334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR","json":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR.json","graph_json":"https://pith.science/api/pith-number/5ODLSPPQG4H5RXUM2DHQHLMOAR/graph.json","events_json":"https://pith.science/api/pith-number/5ODLSPPQG4H5RXUM2DHQHLMOAR/events.json","paper":"https://pith.science/paper/5ODLSPPQ"},"agent_actions":{"view_html":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR","download_json":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR.json","view_paper":"https://pith.science/paper/5ODLSPPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07911&json=true","fetch_graph":"https://pith.science/api/pith-number/5ODLSPPQG4H5RXUM2DHQHLMOAR/graph.json","fetch_events":"https://pith.science/api/pith-number/5ODLSPPQG4H5RXUM2DHQHLMOAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR/action/storage_attestation","attest_author":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR/action/author_attestation","sign_citation":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR/action/citation_signature","submit_replication":"https://pith.science/pith/5ODLSPPQG4H5RXUM2DHQHLMOAR/action/replication_record"}},"created_at":"2026-08-11T01:18:54.413334+00:00","updated_at":"2026-08-11T01:18:54.413334+00:00"}