{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FQ5SJGVGWNBRDMH2FCMSA7COY4","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":"07e6427b0328ee7800006cf98045330255cccbb6d99a55a07fd727fff4f0465f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T04:54:05Z","title_canon_sha256":"c9a2337af6e7d374e5c345a4039cb82e20e4241f2bb0b869cdbc2b74f70510a8"},"schema_version":"1.0","source":{"id":"2210.05144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05144","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05144v1","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05144","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"FQ5SJGVGWNBR","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"FQ5SJGVGWNBRDMH2","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"FQ5SJGVG","created_at":"2026-07-05T05:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:f07b0e23dfdac71f2a1406b99c52cd548ee3a5ce530d7bd323d99cd2d645f92a","target":"graph","created_at":"2026-07-05T05:05:13Z","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/2210.05144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer architecture. This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism. MoA includes a set of attention heads that each has its own set of parameters. Given an input, a router dynamically selects a subset of $k$ attention heads per token. This conditional computation schema allows MoA to achi","authors_text":"Jie Zhou, Wenge Rong, Xiaofeng Zhang, Yikang Shen, Zeyu Huang, Zhang Xiong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T04:54:05Z","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05144","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":"sha256:23a6bcfafc6bcc6f851ee336dbb95c41436b8cbb994469ddf51f9a657cb65a29","target":"record","created_at":"2026-07-05T05:05:13Z","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":"07e6427b0328ee7800006cf98045330255cccbb6d99a55a07fd727fff4f0465f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T04:54:05Z","title_canon_sha256":"c9a2337af6e7d374e5c345a4039cb82e20e4241f2bb0b869cdbc2b74f70510a8"},"schema_version":"1.0","source":{"id":"2210.05144","kind":"arxiv","version":1}},"canonical_sha256":"2c3b249aa6b34311b0fa2899207c4ec72ebde3584c99feced862e108f7a3c190","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c3b249aa6b34311b0fa2899207c4ec72ebde3584c99feced862e108f7a3c190","first_computed_at":"2026-07-05T05:05:13.387637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:13.387637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZPeBeOc2odbbF2puaaeAJpHhx0Rshze87ASL/Zj7GntJsq0/pdhpBVoQpQT+9heQTm5mCNg1VEyGL0fALd9ODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:13.388152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23a6bcfafc6bcc6f851ee336dbb95c41436b8cbb994469ddf51f9a657cb65a29","sha256:f07b0e23dfdac71f2a1406b99c52cd548ee3a5ce530d7bd323d99cd2d645f92a"],"state_sha256":"e8aff46de675ce1dbd3fd78d348f08fa69c3c80573dc1e3da352401743a18bb3"}