{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:22KH7ACB2A5S3F7FX374ZSN4W4","short_pith_number":"pith:22KH7ACB","canonical_record":{"source":{"id":"2112.14397","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T04:52:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52342fb3fc26146aa896f64fc5a6d8939059391652c4aae8f93d6de75cfad74f","abstract_canon_sha256":"e8dff3835e9daea0ea1a3e6a9281a0155952b8c63fdfb693ed1c817c89f5b619"},"schema_version":"1.0"},"canonical_sha256":"d6947f8041d03b2d97e5beffccc9bcb700a28fd28bd3096733a3963ca862cfba","source":{"kind":"arxiv","id":"2112.14397","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:22KH7ACB2A5S3F7FX374ZSN4W4","target":"record","payload":{"canonical_record":{"source":{"id":"2112.14397","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T04:52:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52342fb3fc26146aa896f64fc5a6d8939059391652c4aae8f93d6de75cfad74f","abstract_canon_sha256":"e8dff3835e9daea0ea1a3e6a9281a0155952b8c63fdfb693ed1c817c89f5b619"},"schema_version":"1.0"},"canonical_sha256":"d6947f8041d03b2d97e5beffccc9bcb700a28fd28bd3096733a3963ca862cfba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:26.737671Z","signature_b64":"TJYTkff/5/7ThH31dTKFXawso88OJmk3WlNDIWcr2xPveeXH4RmlT6/8w/ADTc8375DF5Kwt8Q830ekESU2WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6947f8041d03b2d97e5beffccc9bcb700a28fd28bd3096733a3963ca862cfba","last_reissued_at":"2026-07-05T05:04:26.737156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:26.737156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.14397","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkk6VHJXc71RQmAkkT6/Td0HeURGk0wQ/T9AAVPiTA5L2dYeaBLRpuz49PA55QV5PFmc74P8yJdWXeY5lpURBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:16:00.190046Z"},"content_sha256":"33c84a2a7c27b0932ea0dbfb7369d15753d406fd76bd1b302b0df3bc144537cc","schema_version":"1.0","event_id":"sha256:33c84a2a7c27b0932ea0dbfb7369d15753d406fd76bd1b302b0df3bc144537cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:22KH7ACB2A5S3F7FX374ZSN4W4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Jilong Xue, Lingxiao Ma, Qibin Liu, Shijie Cao, Xiaonan Nie, Xupeng Miao, Yi Liu, Youshan Miao, Zhi Yang","submitted_at":"2021-12-29T04:52:14Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14397","kind":"arxiv","version":2},"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/2112.14397/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":"2026-07-05T05:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZSV3gUPn+6nMdknpaVDQb0XuN7XN+/Gonwr4J4AxEOfzuTtEeVw19h42dMunbYoI9M+KwdGSJiCYS7KcLUoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:16:00.190530Z"},"content_sha256":"a45d75aecfbfbeba528f8bdeda560f20bbc8cb2b83dee8f285e5e4aa52f44972","schema_version":"1.0","event_id":"sha256:a45d75aecfbfbeba528f8bdeda560f20bbc8cb2b83dee8f285e5e4aa52f44972"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22KH7ACB2A5S3F7FX374ZSN4W4/bundle.json","state_url":"https://pith.science/pith/22KH7ACB2A5S3F7FX374ZSN4W4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22KH7ACB2A5S3F7FX374ZSN4W4/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":"2026-08-08T01:16:00Z","links":{"resolver":"https://pith.science/pith/22KH7ACB2A5S3F7FX374ZSN4W4","bundle":"https://pith.science/pith/22KH7ACB2A5S3F7FX374ZSN4W4/bundle.json","state":"https://pith.science/pith/22KH7ACB2A5S3F7FX374ZSN4W4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22KH7ACB2A5S3F7FX374ZSN4W4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jjp6vCV7JYfrvgn2+3f5UsI722TGETx1fqEAm7UQmImSbtDMhMHhhJwIYFOLcAst5hCPGnFUBG+qENdEZXdnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:16:00.193965Z","bundle_sha256":"f7ebffda72c573b44e57a343e183aa20c3eb1bf7fb29383495ce5f575fe4a088"}}