{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F5EWWAHSDQICZZDZUXJUKCDHVO","short_pith_number":"pith:F5EWWAHS","canonical_record":{"source":{"id":"2404.16914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T15:39:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"db9fa8f93542770dbda437b161fae4d4864c864188c1115f0f94a5a6ce356348","abstract_canon_sha256":"3dbd31d99e011e33be9ce9f7f2818f56a2db8da3f43c0a4ebbf18333f102d247"},"schema_version":"1.0"},"canonical_sha256":"2f496b00f21c102ce479a5d3450867ab93411fed68f6ae2864f6b06b2f637337","source":{"kind":"arxiv","id":"2404.16914","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16914","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16914v1","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16914","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"F5EWWAHSDQIC","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"F5EWWAHSDQICZZDZ","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"F5EWWAHS","created_at":"2026-07-05T08:12:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F5EWWAHSDQICZZDZUXJUKCDHVO","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T15:39:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"db9fa8f93542770dbda437b161fae4d4864c864188c1115f0f94a5a6ce356348","abstract_canon_sha256":"3dbd31d99e011e33be9ce9f7f2818f56a2db8da3f43c0a4ebbf18333f102d247"},"schema_version":"1.0"},"canonical_sha256":"2f496b00f21c102ce479a5d3450867ab93411fed68f6ae2864f6b06b2f637337","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:32.887011Z","signature_b64":"jZ58RJ7dny9vZlujvZ5afKY60zrNAIWkhv7gOByfaMuYqi4cHZziCmEH5iK5LLZ0dfi4tu7c/P0DqsLW9eD7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f496b00f21c102ce479a5d3450867ab93411fed68f6ae2864f6b06b2f637337","last_reissued_at":"2026-07-05T08:12:32.886561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:32.886561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16914","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":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cVcEuwweHJ94uCQfk51q9EvruoJv6+CD95LRRdmLdR/PWKchMhyDl3+7lTfXrcZ7fzhJPqry2Hje3yis7+9GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:00.459714Z"},"content_sha256":"e1327d203c29103716037acc23d97f792f5c8947637309db740a706aca8a9c32","schema_version":"1.0","event_id":"sha256:e1327d203c29103716037acc23d97f792f5c8947637309db740a706aca8a9c32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F5EWWAHSDQICZZDZUXJUKCDHVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aomufei Yuan, Bowen Ye, Peizhuang Cong, Shimao Chen, Tong Yang, Yuxuan Tian","submitted_at":"2024-04-25T15:39:59Z","abstract_excerpt":"MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing parameters. The learning sparse gating network selects a set of experts for each token to be processed; however, this may lead to differences in the number of tokens processed by each expert over several successive iterations, i.e., the expert load fluctuations, which reduces computational parallelization and resource utilization. To this end, we traced and analyzed loads of each expert in the training iterations for several large language models in this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16914","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/2404.16914/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":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmQ6Cq0WqDLfFRv1iQfDFpldt7a19PZHy++u4zwqLsMD2jvzeRRiyory/ud7Qyg6Aq539ABXjvp0vA6Qz9jkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:00.460221Z"},"content_sha256":"70b0e056dd5f10474705fcf813d1b6f24c1d40fcd71686157c61efd96a2f3208","schema_version":"1.0","event_id":"sha256:70b0e056dd5f10474705fcf813d1b6f24c1d40fcd71686157c61efd96a2f3208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/bundle.json","state_url":"https://pith.science/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/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":"2026-08-08T05:59:00Z","links":{"resolver":"https://pith.science/pith/F5EWWAHSDQICZZDZUXJUKCDHVO","bundle":"https://pith.science/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/bundle.json","state":"https://pith.science/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5EWWAHSDQICZZDZUXJUKCDHVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5EWWAHSDQICZZDZUXJUKCDHVO","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":"3dbd31d99e011e33be9ce9f7f2818f56a2db8da3f43c0a4ebbf18333f102d247","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T15:39:59Z","title_canon_sha256":"db9fa8f93542770dbda437b161fae4d4864c864188c1115f0f94a5a6ce356348"},"schema_version":"1.0","source":{"id":"2404.16914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16914","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16914v1","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16914","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"F5EWWAHSDQIC","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"F5EWWAHSDQICZZDZ","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"F5EWWAHS","created_at":"2026-07-05T08:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:70b0e056dd5f10474705fcf813d1b6f24c1d40fcd71686157c61efd96a2f3208","target":"graph","created_at":"2026-07-05T08:12:32Z","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/2404.16914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing parameters. The learning sparse gating network selects a set of experts for each token to be processed; however, this may lead to differences in the number of tokens processed by each expert over several successive iterations, i.e., the expert load fluctuations, which reduces computational parallelization and resource utilization. To this end, we traced and analyzed loads of each expert in the training iterations for several large language models in this ","authors_text":"Aomufei Yuan, Bowen Ye, Peizhuang Cong, Shimao Chen, Tong Yang, Yuxuan Tian","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T15:39:59Z","title":"Prediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16914","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:e1327d203c29103716037acc23d97f792f5c8947637309db740a706aca8a9c32","target":"record","created_at":"2026-07-05T08:12:32Z","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":"3dbd31d99e011e33be9ce9f7f2818f56a2db8da3f43c0a4ebbf18333f102d247","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T15:39:59Z","title_canon_sha256":"db9fa8f93542770dbda437b161fae4d4864c864188c1115f0f94a5a6ce356348"},"schema_version":"1.0","source":{"id":"2404.16914","kind":"arxiv","version":1}},"canonical_sha256":"2f496b00f21c102ce479a5d3450867ab93411fed68f6ae2864f6b06b2f637337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f496b00f21c102ce479a5d3450867ab93411fed68f6ae2864f6b06b2f637337","first_computed_at":"2026-07-05T08:12:32.886561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:32.886561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZ58RJ7dny9vZlujvZ5afKY60zrNAIWkhv7gOByfaMuYqi4cHZziCmEH5iK5LLZ0dfi4tu7c/P0DqsLW9eD7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:32.887011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1327d203c29103716037acc23d97f792f5c8947637309db740a706aca8a9c32","sha256:70b0e056dd5f10474705fcf813d1b6f24c1d40fcd71686157c61efd96a2f3208"],"state_sha256":"ad9294027f8486028c3fd8e5133a5850ed685f12478983aca5f46b7ca9edf9e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gcM8PmbyEgTj7LPYEXalGvLJcYi/2xAFCQNNpCjRy6Gm4YAdfYmQ5xVA5vqRma0bSFK7SmeuPbKJoK0aHOZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:59:00.463894Z","bundle_sha256":"4249aa3125842c689b3b7cc233031b1f84f3ecc319eddb16c1a216a0ca1ef881"}}