{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XCFF2J62UNVQZ4GDOD2EVQG2XD","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":"f11e59998d49a4dae978be40bebb90bd5c3eae9dc51e054b133a5abf48acb309","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T04:04:39Z","title_canon_sha256":"bd33c757eee372b6193233360361b00e6b869a6bdc8d2ebfe6cc4ce9e9958897"},"schema_version":"1.0","source":{"id":"2501.11873","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11873","created_at":"2026-07-05T10:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11873v2","created_at":"2026-07-05T10:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11873","created_at":"2026-07-05T10:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"XCFF2J62UNVQ","created_at":"2026-07-05T10:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"XCFF2J62UNVQZ4GD","created_at":"2026-07-05T10:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"XCFF2J62","created_at":"2026-07-05T10:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:2bae38d91d07acccae93e88ab093afc4f536c72608860d340c22b9304b05acec","target":"graph","created_at":"2026-07-05T10:09:15Z","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/2501.11873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper revisits the implementation of $\\textbf{L}$oad-$\\textbf{b}$alancing $\\textbf{L}$oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is defined as $N_E \\sum_{i=1}^{N_E} f_i p_i$, where $N_E$ is the total number of experts, $f_i$ represents the frequency of expert $i$ being selected, and $p_i$ denotes the average gating score of the expert $i$. Existing MoE training frameworks usually employ the parallel training strategy so that $f_i$ and the LBL are calculated within a $\\textbf{micro-batch}$ and then averaged across parallel groups. In essence, a mic","authors_text":"Bo Zheng, Dayiheng Liu, Ivan Titov, Jingren Zhou, Junyang Lin, Kaiyue Wen, Rui Men, Zekun Wang, Zeyu Huang, Zihan Qiu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T04:04:39Z","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11873","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":"sha256:097fa69d644dafb398f030ee5d5bf7f54710d96d300471f3d2db52ffe9a05531","target":"record","created_at":"2026-07-05T10:09:15Z","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":"f11e59998d49a4dae978be40bebb90bd5c3eae9dc51e054b133a5abf48acb309","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T04:04:39Z","title_canon_sha256":"bd33c757eee372b6193233360361b00e6b869a6bdc8d2ebfe6cc4ce9e9958897"},"schema_version":"1.0","source":{"id":"2501.11873","kind":"arxiv","version":2}},"canonical_sha256":"b88a5d27daa36b0cf0c370f44ac0dab8cfc32bab66e6f29ea8e467b2b3cecb8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b88a5d27daa36b0cf0c370f44ac0dab8cfc32bab66e6f29ea8e467b2b3cecb8c","first_computed_at":"2026-07-05T10:09:15.108819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:15.108819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vq8Ldh/NlMa/H1IP5MRCLlojI7DC9OvYQFfMqe5mcehaXmbVtX95bC3Cz3FdmV5aT0cSja47qcuosMUOaFt3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:15.109337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11873","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:097fa69d644dafb398f030ee5d5bf7f54710d96d300471f3d2db52ffe9a05531","sha256:2bae38d91d07acccae93e88ab093afc4f536c72608860d340c22b9304b05acec"],"state_sha256":"556c5801fd8d4adffde5dd19abf9f406a95387eaaafa74d6105f005bbafa096a"}