{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSGXXTLRK2YBZ2QC34WXEFZCYZ","short_pith_number":"pith:RSGXXTLR","schema_version":"1.0","canonical_sha256":"8c8d7bcd7156b01cea02df2d721722c6415ad004e573c06d0c40c1e7def7eaed","source":{"kind":"arxiv","id":"2411.16462","version":2},"attestation_state":"computed","paper":{"title":"Lion Cub: Minimizing Communication Overhead in Distributed Lion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Brian Van Essen, Nikoli Dryden, Rio Yokota, Satoki Ishikawa, Tal Ben-Nun","submitted_at":"2024-11-25T15:08:24Z","abstract_excerpt":"Communication overhead is a key challenge in distributed deep learning, especially on slower Ethernet interconnects, and given current hardware trends, communication is likely to become a major bottleneck. While gradient compression techniques have been explored for SGD and Adam, the Lion optimizer has the distinct advantage that its update vectors are the output of a sign operation, enabling straightforward quantization. However, simply compressing updates for communication and using techniques like majority voting fails to lead to end-to-end speedups due to inefficient communication algorith"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.16462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T15:08:24Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"ea3c7703cdc5276cf7e18cd7787eda8283e6d44e06cbaee0aa8ac7a19c688e02","abstract_canon_sha256":"2e64a0bce68442d5deeac6fcb3486188a8141c850b172c2be3b803061430431e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:41.509767Z","signature_b64":"/Y0+9spWTF94DlTu75kaWjwskrSU7XxGVEoQwXA4l6KHbNvT+1Jf7maCXeQ47QgIRSOVDdb7Xq9VZMOUn/GQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8d7bcd7156b01cea02df2d721722c6415ad004e573c06d0c40c1e7def7eaed","last_reissued_at":"2026-07-05T11:31:41.509276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:41.509276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lion Cub: Minimizing Communication Overhead in Distributed Lion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Brian Van Essen, Nikoli Dryden, Rio Yokota, Satoki Ishikawa, Tal Ben-Nun","submitted_at":"2024-11-25T15:08:24Z","abstract_excerpt":"Communication overhead is a key challenge in distributed deep learning, especially on slower Ethernet interconnects, and given current hardware trends, communication is likely to become a major bottleneck. While gradient compression techniques have been explored for SGD and Adam, the Lion optimizer has the distinct advantage that its update vectors are the output of a sign operation, enabling straightforward quantization. However, simply compressing updates for communication and using techniques like majority voting fails to lead to end-to-end speedups due to inefficient communication algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16462","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.16462/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.16462","created_at":"2026-07-05T11:31:41.509335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16462v2","created_at":"2026-07-05T11:31:41.509335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16462","created_at":"2026-07-05T11:31:41.509335+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSGXXTLRK2YB","created_at":"2026-07-05T11:31:41.509335+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSGXXTLRK2YBZ2QC","created_at":"2026-07-05T11:31:41.509335+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSGXXTLR","created_at":"2026-07-05T11:31:41.509335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12327","citing_title":"Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ","json":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ.json","graph_json":"https://pith.science/api/pith-number/RSGXXTLRK2YBZ2QC34WXEFZCYZ/graph.json","events_json":"https://pith.science/api/pith-number/RSGXXTLRK2YBZ2QC34WXEFZCYZ/events.json","paper":"https://pith.science/paper/RSGXXTLR"},"agent_actions":{"view_html":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ","download_json":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ.json","view_paper":"https://pith.science/paper/RSGXXTLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16462&json=true","fetch_graph":"https://pith.science/api/pith-number/RSGXXTLRK2YBZ2QC34WXEFZCYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RSGXXTLRK2YBZ2QC34WXEFZCYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ/action/storage_attestation","attest_author":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ/action/author_attestation","sign_citation":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ/action/citation_signature","submit_replication":"https://pith.science/pith/RSGXXTLRK2YBZ2QC34WXEFZCYZ/action/replication_record"}},"created_at":"2026-07-05T11:31:41.509335+00:00","updated_at":"2026-07-05T11:31:41.509335+00:00"}