{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BW72VCTWHOBTGKCHXZ24AMUXWD","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":"e9561ccade0a66016a4eac719fb6021956eca09823879419048a28d686b844a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-19T05:47:10Z","title_canon_sha256":"6f308517723a2a7629e43ccbf415358fc6e8707ef455029d8ce29500409d56cc"},"schema_version":"1.0","source":{"id":"2406.13233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13233","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13233v2","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13233","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"BW72VCTWHOBT","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"BW72VCTWHOBTGKCH","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"BW72VCTW","created_at":"2026-07-05T09:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:4bbeb9c5f03bc159cda5a5b7fa2e809a6bd8b2c4888a6b9ae52ffaecd8c83775","target":"graph","created_at":"2026-07-05T09:19:59Z","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/2406.13233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture of experts (MoE) has become the standard for constructing production-level large language models (LLMs) due to its promise to boost model capacity without causing significant overheads. Nevertheless, existing MoE methods usually enforce a constant top-k routing for all tokens, which is arguably restrictive because various tokens (e.g., \"<EOS>\" vs. \"apple\") may require various numbers of experts for feature abstraction. Lifting such a constraint can help make the most of limited resources and unleash the potential of the model for downstream tasks. In this sense, we introduce AdaMoE to ","authors_text":"Hao Zhang, Hongcheng Gao, Yibo Miao, Zhijie Deng, Zihao Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-19T05:47:10Z","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13233","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:b639a19f834f839e2f06e3f0432efec9411f71fad1a3478da1a704245a098e74","target":"record","created_at":"2026-07-05T09:19:59Z","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":"e9561ccade0a66016a4eac719fb6021956eca09823879419048a28d686b844a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-19T05:47:10Z","title_canon_sha256":"6f308517723a2a7629e43ccbf415358fc6e8707ef455029d8ce29500409d56cc"},"schema_version":"1.0","source":{"id":"2406.13233","kind":"arxiv","version":2}},"canonical_sha256":"0dbfaa8a763b83332847be75c03297b0c16a31fcb1332317374d441944700664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbfaa8a763b83332847be75c03297b0c16a31fcb1332317374d441944700664","first_computed_at":"2026-07-05T09:19:59.656334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:59.656334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"irkxh50ZDP8hs1XeAxgPkFagB4opoumgZCzUp6l+Z2ADgZFw0gwxXXSMYIZiLvZNKvbLDI7qkvDHmEXmZ3nsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:59.656838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b639a19f834f839e2f06e3f0432efec9411f71fad1a3478da1a704245a098e74","sha256:4bbeb9c5f03bc159cda5a5b7fa2e809a6bd8b2c4888a6b9ae52ffaecd8c83775"],"state_sha256":"f86aafeb74c4272f31d8835bf0d55ba2b882d3497dbda6fba9cf9bf888e283d1"}