{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K45YU5Y2FTQXLIAHVB2NVU3TQY","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":"f984b8207f23e4694f8af087d12e293b6c91f4efad5c34479e6d51dea94133b7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T09:05:08Z","title_canon_sha256":"b156f7fad35ee8605f12b23208f90fb5575fe9f52a84d9a3925cce45988bc9f6"},"schema_version":"1.0","source":{"id":"2405.17976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17976","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17976v2","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17976","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"K45YU5Y2FTQX","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"K45YU5Y2FTQXLIAH","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"K45YU5Y2","created_at":"2026-07-05T08:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:b3460e7b33f2f57ba3e2f7352f42df5fee11fefb04fade75826468cf72b534a3","target":"graph","created_at":"2026-07-05T08:24:25Z","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/2405.17976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Yuan 2.0-M32, with a similar base architecture as Yuan-2.0 2B, uses a mixture-of-experts architecture with 32 experts of which 2 experts are active. A new router network, Attention Router, is proposed and adopted for a more efficient selection of experts, which improves the accuracy compared to the model with classical router network. Yuan 2.0-M32 is trained with 2000B tokens from scratch, and the training computation consumption is only 9.25% of a dense model at the same parameter scale. Yuan 2.0-M32 demonstrates competitive capability on coding, math, and various domains of expertise, with o","authors_text":"Chao Wang, Chong Shen, Fei Wang, Houbo He, Jiangang Luo, Junxiong Mao, Lingjun Li, Shaohua Wu, Tong Yu, Weixu Qiao, Xi Chen, Xudong Zhao, Yue Wang, Zeru Zhang, Zeyu Sun","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T09:05:08Z","title":"Yuan 2.0-M32: Mixture of Experts with Attention Router"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17976","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":"sha256:746b83204fa18ce0f807699c4a92241ee90aae9df9378c443bf3d00e4ad7a17e","target":"record","created_at":"2026-07-05T08:24:25Z","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":"f984b8207f23e4694f8af087d12e293b6c91f4efad5c34479e6d51dea94133b7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T09:05:08Z","title_canon_sha256":"b156f7fad35ee8605f12b23208f90fb5575fe9f52a84d9a3925cce45988bc9f6"},"schema_version":"1.0","source":{"id":"2405.17976","kind":"arxiv","version":2}},"canonical_sha256":"573b8a771a2ce175a007a874dad373862544493f7a438f1805835512d4e083ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"573b8a771a2ce175a007a874dad373862544493f7a438f1805835512d4e083ef","first_computed_at":"2026-07-05T08:24:25.575824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:25.575824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/LT3u7S+CjqvRjDZaRHKYhAtvIeHPHtqWFBH96L3tg7hz322/Qu4vq9XI0FbVXcBIQ5daVlMP+JV6t3HcbQOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:25.576382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:746b83204fa18ce0f807699c4a92241ee90aae9df9378c443bf3d00e4ad7a17e","sha256:b3460e7b33f2f57ba3e2f7352f42df5fee11fefb04fade75826468cf72b534a3"],"state_sha256":"c426bb3b0e14d2a4e5f400ebf6ec8b5ac1c3365a0192c4409a210cfa42d0c924"}