{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QXPUTT2ZKI3PHBF6IZC6467DK2","short_pith_number":"pith:QXPUTT2Z","schema_version":"1.0","canonical_sha256":"85df49cf595236f384be4645ee7be356ad2baebd2f8a681ed615e4c798c410c2","source":{"kind":"arxiv","id":"2608.08650","version":1},"attestation_state":"computed","paper":{"title":"The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiguo Li","submitted_at":"2026-08-09T11:46:29Z","abstract_excerpt":"Mixture-of-Experts models increase parameter capacity while keeping the computation activated by each token bounded, but their architectural evolution cannot be explained by a chronological list of model releases alone. This technical survey synthesizes primary papers, official technical reports, and prior surveys to organize modern Mixture-of-Experts systems along five coupled dimensions: expert granularity, expert topology, routing freedom, the scope of load balancing, and execution structure. We describe eight architectural milestones as a dependency graph with six mainline developments and"},"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":"2608.08650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T11:46:29Z","cross_cats_sorted":[],"title_canon_sha256":"b5b16603be2e3de95b16975078348173ad0e3a63087940f655ae9de73bdb30f9","abstract_canon_sha256":"94d26bb309ca46601b5d376e67f9f8954b0cb3d71b88d4075b8b22e812450cdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:16.726800Z","signature_b64":"ORIW6pWD73gCPu/Y8nn+9hFh2Bv+WxQPfgz02YAwd1LTnhKol51CFFWfk5E7JjJBNS+iKFtzh6LpIqdfuD0BCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85df49cf595236f384be4645ee7be356ad2baebd2f8a681ed615e4c798c410c2","last_reissued_at":"2026-08-11T01:23:16.724289Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:16.724289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiguo Li","submitted_at":"2026-08-09T11:46:29Z","abstract_excerpt":"Mixture-of-Experts models increase parameter capacity while keeping the computation activated by each token bounded, but their architectural evolution cannot be explained by a chronological list of model releases alone. This technical survey synthesizes primary papers, official technical reports, and prior surveys to organize modern Mixture-of-Experts systems along five coupled dimensions: expert granularity, expert topology, routing freedom, the scope of load balancing, and execution structure. We describe eight architectural milestones as a dependency graph with six mainline developments and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08650","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/2608.08650/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":"2608.08650","created_at":"2026-08-11T01:23:16.725104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08650v1","created_at":"2026-08-11T01:23:16.725104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08650","created_at":"2026-08-11T01:23:16.725104+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXPUTT2ZKI3P","created_at":"2026-08-11T01:23:16.725104+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXPUTT2ZKI3PHBF6","created_at":"2026-08-11T01:23:16.725104+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXPUTT2Z","created_at":"2026-08-11T01:23:16.725104+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/QXPUTT2ZKI3PHBF6IZC6467DK2","json":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2.json","graph_json":"https://pith.science/api/pith-number/QXPUTT2ZKI3PHBF6IZC6467DK2/graph.json","events_json":"https://pith.science/api/pith-number/QXPUTT2ZKI3PHBF6IZC6467DK2/events.json","paper":"https://pith.science/paper/QXPUTT2Z"},"agent_actions":{"view_html":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2","download_json":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2.json","view_paper":"https://pith.science/paper/QXPUTT2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08650&json=true","fetch_graph":"https://pith.science/api/pith-number/QXPUTT2ZKI3PHBF6IZC6467DK2/graph.json","fetch_events":"https://pith.science/api/pith-number/QXPUTT2ZKI3PHBF6IZC6467DK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2/action/storage_attestation","attest_author":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2/action/author_attestation","sign_citation":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2/action/citation_signature","submit_replication":"https://pith.science/pith/QXPUTT2ZKI3PHBF6IZC6467DK2/action/replication_record"}},"created_at":"2026-08-11T01:23:16.725104+00:00","updated_at":"2026-08-11T01:23:16.725104+00:00"}