{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPK6NES4K3U4EJVSPPTW6MWZEQ","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":"4302638db42088109bb267acb950ae0401978fc4dd5e5f457e8a8ff02f5a31d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T20:59:20Z","title_canon_sha256":"ccde7b14345b0145dc4727401939c884df1d155c62f9154a4f93473acee50a20"},"schema_version":"1.0","source":{"id":"2407.04153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04153","created_at":"2026-07-05T08:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04153v1","created_at":"2026-07-05T08:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04153","created_at":"2026-07-05T08:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"RPK6NES4K3U4","created_at":"2026-07-05T08:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"RPK6NES4K3U4EJVS","created_at":"2026-07-05T08:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"RPK6NES4","created_at":"2026-07-05T08:40:29Z"}],"graph_snapshots":[{"event_id":"sha256:a55158ee49391789ecdb902a0384063ddfa7e2ae9c7c758047a3a2dea3e54ef7","target":"graph","created_at":"2026-07-05T08:40:29Z","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/2407.04153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The feedforward (FFW) layers in standard transformer architectures incur a linear increase in computational costs and activation memory as the hidden layer width grows. Sparse mixture-of-experts (MoE) architectures have emerged as a viable approach to address this issue by decoupling model size from computational cost. The recent discovery of the fine-grained MoE scaling law shows that higher granularity leads to better performance. However, existing MoE models are limited to a small number of experts due to computational and optimization challenges. This paper introduces PEER (parameter effic","authors_text":"Xu Owen He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T20:59:20Z","title":"Mixture of A Million Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04153","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:c6aedb3fbb2e28df3a8496861c071e82885b13244b92018d779d9a0dc8fdd37a","target":"record","created_at":"2026-07-05T08:40:29Z","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":"4302638db42088109bb267acb950ae0401978fc4dd5e5f457e8a8ff02f5a31d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T20:59:20Z","title_canon_sha256":"ccde7b14345b0145dc4727401939c884df1d155c62f9154a4f93473acee50a20"},"schema_version":"1.0","source":{"id":"2407.04153","kind":"arxiv","version":1}},"canonical_sha256":"8bd5e6925c56e9c226b27be76f32d9243fbf9464358357376743a8452a98eff8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bd5e6925c56e9c226b27be76f32d9243fbf9464358357376743a8452a98eff8","first_computed_at":"2026-07-05T08:40:29.888535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:29.888535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lV6Ra0qXOm9AALxPaVDgCiKJuHG8QqY1MIs/C9q1P9kskV0rx2U1T5mAocawD5VgbqNF/6/5YhfZMjZ5+/d1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:29.888991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6aedb3fbb2e28df3a8496861c071e82885b13244b92018d779d9a0dc8fdd37a","sha256:a55158ee49391789ecdb902a0384063ddfa7e2ae9c7c758047a3a2dea3e54ef7"],"state_sha256":"d65a6aae1b7777bd924c98714f056098b731bc24e0bcf233b17dbf03a4a0f2a6"}