{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3LEOHIE7BWRMK7MVVIKGPZVEHB","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":"e37d3afde9d73e73111506dd9cf1453e88f631b829a12079bdf196e2ac4cbff0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T22:54:21Z","title_canon_sha256":"7192145c2766c989cf619a889fa529b5ac5cc9ca0ac1262f51b03f317e059010"},"schema_version":"1.0","source":{"id":"2505.17331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17331","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17331v2","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17331","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"3LEOHIE7BWRM","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"3LEOHIE7BWRMK7MV","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"3LEOHIE7","created_at":"2026-07-05T11:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:8a1d2e97d536b984bbc6696edc8653209df69f018d227243caf83dc32e61acac","target":"graph","created_at":"2026-07-05T11:25:10Z","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/2505.17331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its learning capacity. ECHO-LLaMA transforms LLaMA models into shared KV caching across certain layers, significantly reducing KV computational complexity while maintaining or improving language performance. Experimental results demonstrate that ECHO-LLaMA achieves up to 77\\% higher token-per-second throughput during training, up to 16\\% higher Model FLOPs Utilization (MFU), and up to 14\\% lower loss when trained on an e","authors_text":"Boxing Chen, Hossein Rajabzadeh, Hyock Ju Kwon, Maryam Dialameh, Omar Mohamed Awad, Rezaul Karim, Walid Ahmed, Yang Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T22:54:21Z","title":"ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17331","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":"sha256:918eef11ec7b260dc188acc82fae0c758ee4f31452dc8c644fd17a2fa25522fe","target":"record","created_at":"2026-07-05T11:25:10Z","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":"e37d3afde9d73e73111506dd9cf1453e88f631b829a12079bdf196e2ac4cbff0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T22:54:21Z","title_canon_sha256":"7192145c2766c989cf619a889fa529b5ac5cc9ca0ac1262f51b03f317e059010"},"schema_version":"1.0","source":{"id":"2505.17331","kind":"arxiv","version":2}},"canonical_sha256":"dac8e3a09f0da2c57d95aa1467e6a4387f217bfa4490bcc9678d10e0b6c0d745","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dac8e3a09f0da2c57d95aa1467e6a4387f217bfa4490bcc9678d10e0b6c0d745","first_computed_at":"2026-07-05T11:25:10.883120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:10.883120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cuCi8buWAezx7LWjCzd0jklc94I0PuSje6aA5LHtLsXlKe7T+oEj5azHWQihVANSrcy1MDSJRLbDGeOK9ftuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:10.883729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:918eef11ec7b260dc188acc82fae0c758ee4f31452dc8c644fd17a2fa25522fe","sha256:8a1d2e97d536b984bbc6696edc8653209df69f018d227243caf83dc32e61acac"],"state_sha256":"0e3668b377a06844e4df938f9f98d7324f5138fe08118308fac13211cc41e5c9"}