{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:22KH7ACB2A5S3F7FX374ZSN4W4","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":"e8dff3835e9daea0ea1a3e6a9281a0155952b8c63fdfb693ed1c817c89f5b619","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T04:52:14Z","title_canon_sha256":"52342fb3fc26146aa896f64fc5a6d8939059391652c4aae8f93d6de75cfad74f"},"schema_version":"1.0","source":{"id":"2112.14397","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.14397","created_at":"2026-07-05T05:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2112.14397v2","created_at":"2026-07-05T05:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14397","created_at":"2026-07-05T05:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"22KH7ACB2A5S","created_at":"2026-07-05T05:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"22KH7ACB2A5S3F7F","created_at":"2026-07-05T05:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"22KH7ACB","created_at":"2026-07-05T05:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:a45d75aecfbfbeba528f8bdeda560f20bbc8cb2b83dee8f285e5e4aa52f44972","target":"graph","created_at":"2026-07-05T05:04:26Z","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/2112.14397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i.e., a small pieces of the full model), MoE can easily increase the model parameters to a very large scale while keeping the computation cost in a constant level. Most existing works just initialize some random experts, set a fixed gating strategy (e.g., Top-k), and train the model from scratch in an ad-hoc way. We identify that these MoE models are suffering from the immature experts and unstable sparse gate, which ","authors_text":"Bin Cui, Jilong Xue, Lingxiao Ma, Qibin Liu, Shijie Cao, Xiaonan Nie, Xupeng Miao, Yi Liu, Youshan Miao, Zhi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T04:52:14Z","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14397","kind":"arxiv","version":2},"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":"sha256:33c84a2a7c27b0932ea0dbfb7369d15753d406fd76bd1b302b0df3bc144537cc","target":"record","created_at":"2026-07-05T05:04:26Z","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":"e8dff3835e9daea0ea1a3e6a9281a0155952b8c63fdfb693ed1c817c89f5b619","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T04:52:14Z","title_canon_sha256":"52342fb3fc26146aa896f64fc5a6d8939059391652c4aae8f93d6de75cfad74f"},"schema_version":"1.0","source":{"id":"2112.14397","kind":"arxiv","version":2}},"canonical_sha256":"d6947f8041d03b2d97e5beffccc9bcb700a28fd28bd3096733a3963ca862cfba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6947f8041d03b2d97e5beffccc9bcb700a28fd28bd3096733a3963ca862cfba","first_computed_at":"2026-07-05T05:04:26.737156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:26.737156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TJYTkff/5/7ThH31dTKFXawso88OJmk3WlNDIWcr2xPveeXH4RmlT6/8w/ADTc8375DF5Kwt8Q830ekESU2WBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:26.737671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.14397","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33c84a2a7c27b0932ea0dbfb7369d15753d406fd76bd1b302b0df3bc144537cc","sha256:a45d75aecfbfbeba528f8bdeda560f20bbc8cb2b83dee8f285e5e4aa52f44972"],"state_sha256":"b4a4960e0be15c329d5382b000cb4b557dfd69a650c55c2793e5ca55def695b6"}