{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6BBRQ4MA57NCEYPZFIT5URYVFN","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":"0b797382e7a5887c7f8619b7bc6510d9acd6060925ac6822193e4c718744be69","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-26T15:45:45Z","title_canon_sha256":"c9e950ba506f4bfa4860ad3fdb6bb991894bf96bc243ef8fd60da5d4f4731d0c"},"schema_version":"1.0","source":{"id":"2412.19255","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19255","created_at":"2026-07-05T10:00:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19255v2","created_at":"2026-07-05T10:00:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19255","created_at":"2026-07-05T10:00:45Z"},{"alias_kind":"pith_short_12","alias_value":"6BBRQ4MA57NC","created_at":"2026-07-05T10:00:45Z"},{"alias_kind":"pith_short_16","alias_value":"6BBRQ4MA57NCEYPZ","created_at":"2026-07-05T10:00:45Z"},{"alias_kind":"pith_short_8","alias_value":"6BBRQ4MA","created_at":"2026-07-05T10:00:45Z"}],"graph_snapshots":[{"event_id":"sha256:0e76d28600fe1b4880fdad094b37bdb30c9d4783337c6ba894b35e2a4dde12d5","target":"graph","created_at":"2026-07-05T10:00:45Z","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/2412.19255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose novel attention architectures, Multi-matrix Factorization Attention (MFA) and MFA-Key-Reuse (MFA-KR). Existing variants for standard Multi-Head Attention (MHA), including SOTA methods like MLA, fail to maintain as strong performance under stringent Key-Value cache (KV cache) constraints. MFA enhances model capacity by efficiently scaling up both the number and dimension of attention heads through low-rank matrix factorization in the Query-Key (QK) circuit. Extending MFA, MFA-KR further reduces memory requirements by repurposing the key cache as value through value projection re-para","authors_text":"Daxin Jiang, Heung-Yeung Shum, Houyi Li, Jingcheng Hu, Shuigeng Zhou, Xiangyu Zhang, Yinmin Zhang, Zili Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-26T15:45:45Z","title":"Multi-matrix Factorization Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19255","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:f36957f505b2b5b947b2942baa6ae40d8491d5042b4bc3596e3a41fc11a7e901","target":"record","created_at":"2026-07-05T10:00:45Z","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":"0b797382e7a5887c7f8619b7bc6510d9acd6060925ac6822193e4c718744be69","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-26T15:45:45Z","title_canon_sha256":"c9e950ba506f4bfa4860ad3fdb6bb991894bf96bc243ef8fd60da5d4f4731d0c"},"schema_version":"1.0","source":{"id":"2412.19255","kind":"arxiv","version":2}},"canonical_sha256":"f043187180efda2261f92a27da47152b5d8db587eb37659aa4128dea346384d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f043187180efda2261f92a27da47152b5d8db587eb37659aa4128dea346384d3","first_computed_at":"2026-07-05T10:00:45.357737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:45.357737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GnDetOsmO+ddcMFUfH5abe15KH4m8mLdqJyZUKfJ+OmErUp9RWXVjUxVAeaCc1ciCBkamfdqtRPDZkahoujQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:45.358304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19255","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f36957f505b2b5b947b2942baa6ae40d8491d5042b4bc3596e3a41fc11a7e901","sha256:0e76d28600fe1b4880fdad094b37bdb30c9d4783337c6ba894b35e2a4dde12d5"],"state_sha256":"89f3b97624fb67704e23494acae0b2f9a4b30d915898da34a3cc75ad0b66d28a"}