{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LOC5Y6S5MCHLHIKTNDMULMZYDZ","short_pith_number":"pith:LOC5Y6S5","canonical_record":{"source":{"id":"2506.07366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T02:32:09Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"7f2d0a0fefacef646d146102d5e0c77be23ec76b7f23789f59e224c4fe11c32e","abstract_canon_sha256":"654ebca29795465fbe723cec9b07be0ab7965aaa3afa136f6cc4f3236262700a"},"schema_version":"1.0"},"canonical_sha256":"5b85dc7a5d608eb3a15368d945b3381e7f0bbe578e45209f0c101ecafe41d89f","source":{"kind":"arxiv","id":"2506.07366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07366","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07366v1","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07366","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"LOC5Y6S5MCHL","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"LOC5Y6S5MCHLHIKT","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"LOC5Y6S5","created_at":"2026-07-05T11:18:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LOC5Y6S5MCHLHIKTNDMULMZYDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T02:32:09Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"7f2d0a0fefacef646d146102d5e0c77be23ec76b7f23789f59e224c4fe11c32e","abstract_canon_sha256":"654ebca29795465fbe723cec9b07be0ab7965aaa3afa136f6cc4f3236262700a"},"schema_version":"1.0"},"canonical_sha256":"5b85dc7a5d608eb3a15368d945b3381e7f0bbe578e45209f0c101ecafe41d89f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:25.871867Z","signature_b64":"gH9jxfdHv9ZHaNMngyL8SLjwOkI6Fp+bwC+CUUYpaqtm+S6k3S+RUUbWYGFLdl3qkBo4ZWwHFLhAjBOxJiD2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b85dc7a5d608eb3a15368d945b3381e7f0bbe578e45209f0c101ecafe41d89f","last_reissued_at":"2026-07-05T11:18:25.871356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:25.871356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07366","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKrAN/gEdR3R9UKIRm4VRewpOu1bV1W2VBv42hekSZdwlofttQemNtRDndfo4JawP9Jg6Ab+4s/RLEhZDQt7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:54:29.148046Z"},"content_sha256":"7b492aed37058ea957795233eece1a47bb380ac44958b12deabb3fa242d35302","schema_version":"1.0","event_id":"sha256:7b492aed37058ea957795233eece1a47bb380ac44958b12deabb3fa242d35302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LOC5Y6S5MCHLHIKTNDMULMZYDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Haiyue Ma, Yiran Chen, Zhixu Du","submitted_at":"2025-06-09T02:32:09Z","abstract_excerpt":"In multi-GPU Mixture-of-Experts (MoE) network, experts are distributed across different GPUs, which creates load imbalance as each expert processes different number of tokens. Recent works improve MoE inference load balance by dynamically duplicating popular experts to more GPUs to process excessive tokens, which requires predicting the distribution before routing. In this paper, we discuss the tradeoff of prediction strategies, accuracies, overhead, and end-to-end system performance. We propose MoE-GPS, a framework that guides the selection of the optimal predictor design under various system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07366","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/2506.07366/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bg+VJD9IqrqFxlwPFh/dOcZVoAUmq1FSSbNPlJZTLwurMgNjn4Y4kHMlziOMBYw0ViTRGRsDc2HUtZG6OyzADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:54:29.148612Z"},"content_sha256":"f83b6006c0488d970c7da0765b86d8582b03be327dbb023715129fe6e686ea9b","schema_version":"1.0","event_id":"sha256:f83b6006c0488d970c7da0765b86d8582b03be327dbb023715129fe6e686ea9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/bundle.json","state_url":"https://pith.science/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T08:54:29Z","links":{"resolver":"https://pith.science/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ","bundle":"https://pith.science/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/bundle.json","state":"https://pith.science/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOC5Y6S5MCHLHIKTNDMULMZYDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LOC5Y6S5MCHLHIKTNDMULMZYDZ","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":"654ebca29795465fbe723cec9b07be0ab7965aaa3afa136f6cc4f3236262700a","cross_cats_sorted":["cs.AR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T02:32:09Z","title_canon_sha256":"7f2d0a0fefacef646d146102d5e0c77be23ec76b7f23789f59e224c4fe11c32e"},"schema_version":"1.0","source":{"id":"2506.07366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07366","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07366v1","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07366","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"LOC5Y6S5MCHL","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"LOC5Y6S5MCHLHIKT","created_at":"2026-07-05T11:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"LOC5Y6S5","created_at":"2026-07-05T11:18:25Z"}],"graph_snapshots":[{"event_id":"sha256:f83b6006c0488d970c7da0765b86d8582b03be327dbb023715129fe6e686ea9b","target":"graph","created_at":"2026-07-05T11:18:25Z","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/2506.07366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-GPU Mixture-of-Experts (MoE) network, experts are distributed across different GPUs, which creates load imbalance as each expert processes different number of tokens. Recent works improve MoE inference load balance by dynamically duplicating popular experts to more GPUs to process excessive tokens, which requires predicting the distribution before routing. In this paper, we discuss the tradeoff of prediction strategies, accuracies, overhead, and end-to-end system performance. We propose MoE-GPS, a framework that guides the selection of the optimal predictor design under various system","authors_text":"Haiyue Ma, Yiran Chen, Zhixu Du","cross_cats":["cs.AR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T02:32:09Z","title":"MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07366","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":"sha256:7b492aed37058ea957795233eece1a47bb380ac44958b12deabb3fa242d35302","target":"record","created_at":"2026-07-05T11:18:25Z","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":"654ebca29795465fbe723cec9b07be0ab7965aaa3afa136f6cc4f3236262700a","cross_cats_sorted":["cs.AR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T02:32:09Z","title_canon_sha256":"7f2d0a0fefacef646d146102d5e0c77be23ec76b7f23789f59e224c4fe11c32e"},"schema_version":"1.0","source":{"id":"2506.07366","kind":"arxiv","version":1}},"canonical_sha256":"5b85dc7a5d608eb3a15368d945b3381e7f0bbe578e45209f0c101ecafe41d89f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b85dc7a5d608eb3a15368d945b3381e7f0bbe578e45209f0c101ecafe41d89f","first_computed_at":"2026-07-05T11:18:25.871356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:25.871356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gH9jxfdHv9ZHaNMngyL8SLjwOkI6Fp+bwC+CUUYpaqtm+S6k3S+RUUbWYGFLdl3qkBo4ZWwHFLhAjBOxJiD2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:25.871867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b492aed37058ea957795233eece1a47bb380ac44958b12deabb3fa242d35302","sha256:f83b6006c0488d970c7da0765b86d8582b03be327dbb023715129fe6e686ea9b"],"state_sha256":"f6996dbf2e7f513ad53cc983c3e5d721e228b85d1a23b1620e56f11e53a992ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPYInTd0g+fe9BI6cxiYrpaVeGATpU7JH/ClEN5dO00oxddXhXroW8GYRuMamAuWZKOTFyJ5BL6DclfE235iCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:54:29.154207Z","bundle_sha256":"060184fab72db2c0ce0cac91c0340c1f27704de8d3434d0590c472992496c520"}}