{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M245ZHWACQGBIXAYNSZZ2VHP75","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":"ed4e22549071b4c834fe8b3d2cdb1b6862f4f5f8276bdf475f493b90b3770407","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T13:06:17Z","title_canon_sha256":"b6895c9d7038f6abcdbd0f185e91a2a6b944fe14de8c5750a1c603cd00132092"},"schema_version":"1.0","source":{"id":"2411.02063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02063","created_at":"2026-07-05T09:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02063v1","created_at":"2026-07-05T09:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02063","created_at":"2026-07-05T09:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"M245ZHWACQGB","created_at":"2026-07-05T09:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"M245ZHWACQGBIXAY","created_at":"2026-07-05T09:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"M245ZHWA","created_at":"2026-07-05T09:30:40Z"}],"graph_snapshots":[{"event_id":"sha256:167a99aa188fdcfce65e661b51cf884a9cf862029d812611e86126980a44537b","target":"graph","created_at":"2026-07-05T09:30:40Z","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/2411.02063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will compromise performance, can be scalably effective when reduced parameters are precisely targeted. Specifically, applying the low-dimensional module only to the attention layer -- resolves this issue and enhances both effectiveness and efficiency. We refer to this structure as Low-dimensional Projected Attention (LPA) and provide an explanatory analysis. Through","authors_text":"Bowen Zhou, Ermo Hua, Ganqu Cui, Kaiyan Zhang, Ning Ding, Xingtai Lv","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T13:06:17Z","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02063","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:d1a9ed2d2631214beff6977acdafd0d545214cc411bfe2ac4c84a9548ac5c60d","target":"record","created_at":"2026-07-05T09:30:40Z","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":"ed4e22549071b4c834fe8b3d2cdb1b6862f4f5f8276bdf475f493b90b3770407","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T13:06:17Z","title_canon_sha256":"b6895c9d7038f6abcdbd0f185e91a2a6b944fe14de8c5750a1c603cd00132092"},"schema_version":"1.0","source":{"id":"2411.02063","kind":"arxiv","version":1}},"canonical_sha256":"66b9dc9ec0140c145c186cb39d54efff5d923d3bad1e5f495067a9c0ee2c31c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66b9dc9ec0140c145c186cb39d54efff5d923d3bad1e5f495067a9c0ee2c31c3","first_computed_at":"2026-07-05T09:30:40.770432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:40.770432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWFY6caHtiGLGfDwNju7lHN4LEnAX46DWxXyKgI9S3XE0T2MIRQHrLMDxCPeMiYEiRoRDwN1ZpzepqJ5wETwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:40.770973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1a9ed2d2631214beff6977acdafd0d545214cc411bfe2ac4c84a9548ac5c60d","sha256:167a99aa188fdcfce65e661b51cf884a9cf862029d812611e86126980a44537b"],"state_sha256":"5e5ef06a125e8bc07983f140c6a382a5d28ac48eafb028f413cc3cc8bbba43b4"}