{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSOUZLYLQCDIDOJJYZEFEQLXEX","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":"d4d9bef36b9134d7310cba5971c99f41a118071b27018207e8b3c1091ad8ea4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T10:53:47Z","title_canon_sha256":"0cce9fca24973be8a517078b37782cac914db0d3c85179879ddfcf0abcdb55cb"},"schema_version":"1.0","source":{"id":"2505.05950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05950","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05950v2","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05950","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"WSOUZLYLQCDI","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"WSOUZLYLQCDIDOJJ","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"WSOUZLYL","created_at":"2026-07-05T11:01:37Z"}],"graph_snapshots":[{"event_id":"sha256:b82ebe2757af974d9e6b04609da1c075b912e6da656dce38f558ab560437755f","target":"graph","created_at":"2026-07-05T11:01:37Z","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/2505.05950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has emerged as a potential solution, the large size of activated experts overburdens the limited PCIe bandwidth, hindering the effectiveness in latency-sensitive scenarios. To mitigate this, we propose FloE, an on-the-fly MoE inference system on memory-constrained GPUs. FloE is built on the insight that there exists substantial untapped redundancy within sparsely","authors_text":"Jue Wang, Jun Zhang, Ke Chen, Lidan Shou, Yiping Wang, Yuxin Zhou, Zheng Li, Zhongle Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T10:53:47Z","title":"FloE: On-the-Fly MoE Inference on Memory-constrained GPU"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05950","kind":"arxiv","version":2},"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":"sha256:9a1a7a1bb693c59edd5a4d5708c7281ec63e9db37a71c3e22146a7f33db0c0c6","target":"record","created_at":"2026-07-05T11:01:37Z","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":"d4d9bef36b9134d7310cba5971c99f41a118071b27018207e8b3c1091ad8ea4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T10:53:47Z","title_canon_sha256":"0cce9fca24973be8a517078b37782cac914db0d3c85179879ddfcf0abcdb55cb"},"schema_version":"1.0","source":{"id":"2505.05950","kind":"arxiv","version":2}},"canonical_sha256":"b49d4caf0b808681b929c64852417725c496c9269ba9cefe0da9582805f72deb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b49d4caf0b808681b929c64852417725c496c9269ba9cefe0da9582805f72deb","first_computed_at":"2026-07-05T11:01:37.220895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:37.220895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQliAxe087cdFR/zCzPoFRqhxlcToHvpzd/Y/rNblOF6FzY20WBqmFnZrHRrVMThBCzBIrrpBVWf379XBM3rDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:37.221383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a1a7a1bb693c59edd5a4d5708c7281ec63e9db37a71c3e22146a7f33db0c0c6","sha256:b82ebe2757af974d9e6b04609da1c075b912e6da656dce38f558ab560437755f"],"state_sha256":"2c308c6c9bec3b5baa0bf5cbbc0be6f78e16a4dc969c835af7b5250b05ceb1ce"}