{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LTIA47SD7O5VD7S3PMFMZ67QSS","short_pith_number":"pith:LTIA47SD","canonical_record":{"source":{"id":"2208.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-04T17:59:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a6fc029334adb845a75a4113d6b511750ff48565dc77798c0286e23b03861bff","abstract_canon_sha256":"7a5bca50df694056e93ef155fa3c02d6fc88106257ca838e6f8ed3469f610f51"},"schema_version":"1.0"},"canonical_sha256":"5cd00e7e43fbbb51fe5b7b0accfbf094856d4ef0ae1f60c0974947ebe06ec660","source":{"kind":"arxiv","id":"2208.02813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.02813","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2208.02813v1","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02813","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"LTIA47SD7O5V","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"LTIA47SD7O5VD7S3","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"LTIA47SD","created_at":"2026-07-05T04:46:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LTIA47SD7O5VD7S3PMFMZ67QSS","target":"record","payload":{"canonical_record":{"source":{"id":"2208.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-04T17:59:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a6fc029334adb845a75a4113d6b511750ff48565dc77798c0286e23b03861bff","abstract_canon_sha256":"7a5bca50df694056e93ef155fa3c02d6fc88106257ca838e6f8ed3469f610f51"},"schema_version":"1.0"},"canonical_sha256":"5cd00e7e43fbbb51fe5b7b0accfbf094856d4ef0ae1f60c0974947ebe06ec660","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:09.297411Z","signature_b64":"JBriCSZJJoaqWTHTTGtQ1n2m9u5Ho+a10p8IeZe7gGsodn8XLOS1EppyandWkkJN9BFJ0a1NzvKXpM3EGZUdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cd00e7e43fbbb51fe5b7b0accfbf094856d4ef0ae1f60c0974947ebe06ec660","last_reissued_at":"2026-07-05T04:46:09.296942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:09.296942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.02813","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":"2026-07-05T04:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rytzbaal1hFFTlDyVxUKEq8896df1dDawn3A+myVlhT1mOVlG0CpReEmk4SQT/OQP+mYffCu5BDdrpEqrAIhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:20:01.317764Z"},"content_sha256":"1d823f5753bb5991ef48cd7981e7ab86c482bb9e5e554dc3d97ba259c9d49952","schema_version":"1.0","event_id":"sha256:1d823f5753bb5991ef48cd7981e7ab86c482bb9e5e554dc3d97ba259c9d49952"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LTIA47SD7O5VD7S3PMFMZ67QSS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding Mixture of Experts in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Quanquan Gu, Yihe Deng, Yuanzhi Li, Yue Wu, Zixiang Chen","submitted_at":"2022-08-04T17:59:10Z","abstract_excerpt":"The Mixture-of-Experts (MoE) layer, a sparsely-activated model controlled by a router, has achieved great success in deep learning. However, the understanding of such architecture remains elusive. In this paper, we formally study how the MoE layer improves the performance of neural network learning and why the mixture model will not collapse into a single model. Our empirical results suggest that the cluster structure of the underlying problem and the non-linearity of the expert are pivotal to the success of MoE. To further understand this, we consider a challenging classification problem with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02813","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/2208.02813/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":"2026-07-05T04:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwQ8Y1jcfjlxHwAqtp2j53yS6dU7o/GharEOlsSOFzF3WUYwb/hpynNbkHbRYU3DstcLnXavcBUBip8thCcDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:20:01.318506Z"},"content_sha256":"047ff2af6bc5de1f60d43cbfae65b753270a56be9cc8a23437f6b88ff3f60284","schema_version":"1.0","event_id":"sha256:047ff2af6bc5de1f60d43cbfae65b753270a56be9cc8a23437f6b88ff3f60284"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/bundle.json","state_url":"https://pith.science/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/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":"2026-08-10T01:20:01Z","links":{"resolver":"https://pith.science/pith/LTIA47SD7O5VD7S3PMFMZ67QSS","bundle":"https://pith.science/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/bundle.json","state":"https://pith.science/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTIA47SD7O5VD7S3PMFMZ67QSS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LTIA47SD7O5VD7S3PMFMZ67QSS","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":"7a5bca50df694056e93ef155fa3c02d6fc88106257ca838e6f8ed3469f610f51","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-04T17:59:10Z","title_canon_sha256":"a6fc029334adb845a75a4113d6b511750ff48565dc77798c0286e23b03861bff"},"schema_version":"1.0","source":{"id":"2208.02813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.02813","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2208.02813v1","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02813","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"LTIA47SD7O5V","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"LTIA47SD7O5VD7S3","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"LTIA47SD","created_at":"2026-07-05T04:46:09Z"}],"graph_snapshots":[{"event_id":"sha256:047ff2af6bc5de1f60d43cbfae65b753270a56be9cc8a23437f6b88ff3f60284","target":"graph","created_at":"2026-07-05T04:46:09Z","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/2208.02813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mixture-of-Experts (MoE) layer, a sparsely-activated model controlled by a router, has achieved great success in deep learning. However, the understanding of such architecture remains elusive. In this paper, we formally study how the MoE layer improves the performance of neural network learning and why the mixture model will not collapse into a single model. Our empirical results suggest that the cluster structure of the underlying problem and the non-linearity of the expert are pivotal to the success of MoE. To further understand this, we consider a challenging classification problem with","authors_text":"Quanquan Gu, Yihe Deng, Yuanzhi Li, Yue Wu, Zixiang Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-04T17:59:10Z","title":"Towards Understanding Mixture of Experts in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02813","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":"sha256:1d823f5753bb5991ef48cd7981e7ab86c482bb9e5e554dc3d97ba259c9d49952","target":"record","created_at":"2026-07-05T04:46:09Z","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":"7a5bca50df694056e93ef155fa3c02d6fc88106257ca838e6f8ed3469f610f51","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-04T17:59:10Z","title_canon_sha256":"a6fc029334adb845a75a4113d6b511750ff48565dc77798c0286e23b03861bff"},"schema_version":"1.0","source":{"id":"2208.02813","kind":"arxiv","version":1}},"canonical_sha256":"5cd00e7e43fbbb51fe5b7b0accfbf094856d4ef0ae1f60c0974947ebe06ec660","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cd00e7e43fbbb51fe5b7b0accfbf094856d4ef0ae1f60c0974947ebe06ec660","first_computed_at":"2026-07-05T04:46:09.296942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:09.296942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JBriCSZJJoaqWTHTTGtQ1n2m9u5Ho+a10p8IeZe7gGsodn8XLOS1EppyandWkkJN9BFJ0a1NzvKXpM3EGZUdBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:09.297411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.02813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d823f5753bb5991ef48cd7981e7ab86c482bb9e5e554dc3d97ba259c9d49952","sha256:047ff2af6bc5de1f60d43cbfae65b753270a56be9cc8a23437f6b88ff3f60284"],"state_sha256":"1f916324cc70a8f15738b248b13ed805a28c627a3e20a9d1326216be39926058"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a51lndfOpFYrC/BgPlpZmGSb/t4QODlHM6blLbm6wiTJwwMOvTnecwhdgA3YUkYzZA8K0WbSml/jcf8AUYY/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:20:01.325154Z","bundle_sha256":"412feee304374fecc34c21678dcee3f1d510e0de8392d47f0ba1e51aa32219aa"}}