{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3GYUN2URXR4SPLVCCPMWVP2NLY","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":"a2f38cc38a2d019bd261b3101b0273068ed9e8cf7cfcdf51e61435f55899f190","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T07:33:11Z","title_canon_sha256":"c1a9aa2c565c61950e91088223854ebe008931488f47e65d11972ba7f28ee073"},"schema_version":"1.0","source":{"id":"2508.18756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18756","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18756v1","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18756","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"3GYUN2URXR4S","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"3GYUN2URXR4SPLVC","created_at":"2026-07-05T11:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"3GYUN2UR","created_at":"2026-07-05T11:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:638715331acb3d7e8b6ee7745367bc761e8f903cb7edc504b65540d2bbfecb7c","target":"graph","created_at":"2026-07-05T11:59:30Z","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/2508.18756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures offer an appealing alternative with very few memory access, but previous attempts like UltraMem have only matched the performance of 2-expert MoE models, falling significantly short of state-of-the-art 8-expert configurations. We present UltraMemV2, a redesigned memory-layer architecture that closes this performance gap. Our approach introduces five key improvements: integrating memory layers into ev","authors_text":"Banggu Wu, Defa Zhu, Hongzhi Huang, Qiyang Min, Ran Guo, Siyan Chen, Siyuan Qiao, Xun Zhou, Yu Bao, Yutao Zeng, Zihao Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T07:33:11Z","title":"UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18756","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":"sha256:12bcbbee10cfb06c02a124701b0e63ff56cdb8affb5f565340fb9328b6328ac9","target":"record","created_at":"2026-07-05T11:59:30Z","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":"a2f38cc38a2d019bd261b3101b0273068ed9e8cf7cfcdf51e61435f55899f190","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T07:33:11Z","title_canon_sha256":"c1a9aa2c565c61950e91088223854ebe008931488f47e65d11972ba7f28ee073"},"schema_version":"1.0","source":{"id":"2508.18756","kind":"arxiv","version":1}},"canonical_sha256":"d9b146ea91bc7927aea213d96abf4d5e3e4faf439bca2cfbad570922b03a5b60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9b146ea91bc7927aea213d96abf4d5e3e4faf439bca2cfbad570922b03a5b60","first_computed_at":"2026-07-05T11:59:30.289607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:30.289607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZJSVegK+KXo9QK2J+PJL/DK4Y8XyvzEqHcJGVxZ2PSBUqYqzXsnBYNmEHsVedaCwyvdnuKEt7fHYDMQ5KHbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:30.290028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12bcbbee10cfb06c02a124701b0e63ff56cdb8affb5f565340fb9328b6328ac9","sha256:638715331acb3d7e8b6ee7745367bc761e8f903cb7edc504b65540d2bbfecb7c"],"state_sha256":"7de7a8615602cd855339741bcd378c6448e27ad0e4325b7f8affcd26232e7fe5"}