{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:32VBHWKAHC63CZA2QXX2YV5T2L","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":"cf71efedba4762f5de7377d390302e28d7396655dfb645d9b578ecb551b6050e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T13:47:09Z","title_canon_sha256":"ec56aea08cbed81c81424d285544960544b50f5e3c7136ef39e984965fe05328"},"schema_version":"1.0","source":{"id":"2404.15045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15045","created_at":"2026-07-05T08:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15045v1","created_at":"2026-07-05T08:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15045","created_at":"2026-07-05T08:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"32VBHWKAHC63","created_at":"2026-07-05T08:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"32VBHWKAHC63CZA2","created_at":"2026-07-05T08:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"32VBHWKA","created_at":"2026-07-05T08:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:754f81c8166544c43be29ee377a155301e81743c249d86ddbbde0821fe75a8d0","target":"graph","created_at":"2026-07-05T08:11:14Z","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/2404.15045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activation, where only a small subset of experts are activated for optimization. (2) Lacking fine-grained analytical capabilities for multiple semantic concepts within individual tokens. We propose Multi-Head Mixture-of-Experts (MH-MoE), which employs a multi-head mechanism to split each token into multiple sub-tokens. These sub-tokens are then assigned to and processed by a diverse set of experts in parallel, and seamlessl","authors_text":"Furu Wei, Shaohan Huang, Wenhui Wang, Xun Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T13:47:09Z","title":"Multi-Head Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15045","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:b372d1f87f8a894ae9bbd3bc3e01a8e7df0aa3679e70ec335c63793c2755c10e","target":"record","created_at":"2026-07-05T08:11:14Z","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":"cf71efedba4762f5de7377d390302e28d7396655dfb645d9b578ecb551b6050e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T13:47:09Z","title_canon_sha256":"ec56aea08cbed81c81424d285544960544b50f5e3c7136ef39e984965fe05328"},"schema_version":"1.0","source":{"id":"2404.15045","kind":"arxiv","version":1}},"canonical_sha256":"deaa13d94038bdb1641a85efac57b3d2ccef2df2cff9ab933f0e6908ce444d27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"deaa13d94038bdb1641a85efac57b3d2ccef2df2cff9ab933f0e6908ce444d27","first_computed_at":"2026-07-05T08:11:14.460493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:14.460493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FtPSUj3Y9xtgtWj34t4UTPNaXvH/DjdKZgL71TQ3ZivjlH1jVN3OQgnUgDB8sioH277XJ8/2gjOaSeFYlJAZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:14.460982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b372d1f87f8a894ae9bbd3bc3e01a8e7df0aa3679e70ec335c63793c2755c10e","sha256:754f81c8166544c43be29ee377a155301e81743c249d86ddbbde0821fe75a8d0"],"state_sha256":"76faea26487f1b9088f2b2b395b80c0d9ca182e6a9dce59b17d0b3d20b83f8a3"}