{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RPK6NES4K3U4EJVSPPTW6MWZEQ","short_pith_number":"pith:RPK6NES4","canonical_record":{"source":{"id":"2407.04153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T20:59:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccde7b14345b0145dc4727401939c884df1d155c62f9154a4f93473acee50a20","abstract_canon_sha256":"4302638db42088109bb267acb950ae0401978fc4dd5e5f457e8a8ff02f5a31d6"},"schema_version":"1.0"},"canonical_sha256":"8bd5e6925c56e9c226b27be76f32d9243fbf9464358357376743a8452a98eff8","source":{"kind":"arxiv","id":"2407.04153","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RPK6NES4K3U4EJVSPPTW6MWZEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T20:59:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccde7b14345b0145dc4727401939c884df1d155c62f9154a4f93473acee50a20","abstract_canon_sha256":"4302638db42088109bb267acb950ae0401978fc4dd5e5f457e8a8ff02f5a31d6"},"schema_version":"1.0"},"canonical_sha256":"8bd5e6925c56e9c226b27be76f32d9243fbf9464358357376743a8452a98eff8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:29.888991Z","signature_b64":"lV6Ra0qXOm9AALxPaVDgCiKJuHG8QqY1MIs/C9q1P9kskV0rx2U1T5mAocawD5VgbqNF/6/5YhfZMjZ5+/d1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd5e6925c56e9c226b27be76f32d9243fbf9464358357376743a8452a98eff8","last_reissued_at":"2026-07-05T08:40:29.888535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:29.888535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04153","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":"2026-07-05T08:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zw0rP7D3JeFv1Rt86SnxH6MpAYUh/TDYJshSQOc3ze+PVYWlGVQen+HqbHNInNV1BYBSbTfbPvFM19+RkaJNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:52:34.953560Z"},"content_sha256":"c6aedb3fbb2e28df3a8496861c071e82885b13244b92018d779d9a0dc8fdd37a","schema_version":"1.0","event_id":"sha256:c6aedb3fbb2e28df3a8496861c071e82885b13244b92018d779d9a0dc8fdd37a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RPK6NES4K3U4EJVSPPTW6MWZEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixture of A Million Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xu Owen He","submitted_at":"2024-07-04T20:59:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04153","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/2407.04153/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":"2026-07-05T08:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+R5OW5E+yJ0sXp+IlmAk+9Bi67BupLsyPJCC13XeRmqIQ8FpLwV0b+FwzKGSBp+FjyTw1bObLTNWuuV+eKYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:52:34.954103Z"},"content_sha256":"a55158ee49391789ecdb902a0384063ddfa7e2ae9c7c758047a3a2dea3e54ef7","schema_version":"1.0","event_id":"sha256:a55158ee49391789ecdb902a0384063ddfa7e2ae9c7c758047a3a2dea3e54ef7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/bundle.json","state_url":"https://pith.science/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/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":"2026-08-06T06:52:34Z","links":{"resolver":"https://pith.science/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ","bundle":"https://pith.science/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/bundle.json","state":"https://pith.science/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPK6NES4K3U4EJVSPPTW6MWZEQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIyfLApMc6hwKn9+2UP+ahoahVk9z4oJ4lauOoyD9a57kypAkVnMeWWOMyU1Xf8HyC6QZ4mN+TzI7Se4gJk1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:52:34.957277Z","bundle_sha256":"76799646a6fab9e92ecb4845a59c311bdd547fc2c635e9c9144c0259208115c3"}}