{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CHJ5KWTGN6DNXVXUMPALR6BAQB","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":"231b27a093e251cf55ccc01a8f0df0b971989722e09ecd01a4bd0757e469ad58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T15:08:32Z","title_canon_sha256":"049ede9a0d05d96834a587df751ce4052af7a682e64c357eded4108b9ea08376"},"schema_version":"1.0","source":{"id":"2310.06003","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06003","created_at":"2026-07-05T07:06:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06003v2","created_at":"2026-07-05T07:06:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06003","created_at":"2026-07-05T07:06:35Z"},{"alias_kind":"pith_short_12","alias_value":"CHJ5KWTGN6DN","created_at":"2026-07-05T07:06:35Z"},{"alias_kind":"pith_short_16","alias_value":"CHJ5KWTGN6DNXVXU","created_at":"2026-07-05T07:06:35Z"},{"alias_kind":"pith_short_8","alias_value":"CHJ5KWTG","created_at":"2026-07-05T07:06:35Z"}],"graph_snapshots":[{"event_id":"sha256:64396b4660bfed8e25e10f204415b9ed2a65c3d4c5053c651183b3d56914e7f0","target":"graph","created_at":"2026-07-05T07:06:35Z","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/2310.06003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, various distributed strategies for large language model training have been proposed. However, these methods provided limited solutions for the trade-off between memory consumption and communication cost. In this paper, we rethink the impact of memory consumption and communication costs on the training speed of large language models, and propose a memory-communication balanced strategy set Partial Redundancy Optimizer (PaRO). PaRO provides comprehensive options which reduces the amount and frequency of inter-group communication with minor memory redundancy by fine-grained sharding str","authors_text":"Chan Wu, Fanzhuang Meng, Hanxiao Zhang, Jinjing Huang, Jun Zhou, Lei Liang, Lin Ju, Siyuan Li, Xiaolu Zhang, Youshao Xiao, Zhaoxin Huan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T15:08:32Z","title":"Rethinking Memory and Communication Cost for Efficient Large Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06003","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":"sha256:3e096df085803e65e356185b870d6840b2f0c2aa2f685ac62a5a0c240e832366","target":"record","created_at":"2026-07-05T07:06:35Z","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":"231b27a093e251cf55ccc01a8f0df0b971989722e09ecd01a4bd0757e469ad58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T15:08:32Z","title_canon_sha256":"049ede9a0d05d96834a587df751ce4052af7a682e64c357eded4108b9ea08376"},"schema_version":"1.0","source":{"id":"2310.06003","kind":"arxiv","version":2}},"canonical_sha256":"11d3d55a666f86dbd6f463c0b8f820806d9bdc84a7e41c3ec72c57a984984304","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11d3d55a666f86dbd6f463c0b8f820806d9bdc84a7e41c3ec72c57a984984304","first_computed_at":"2026-07-05T07:06:35.745332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:35.745332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GgTeQ3MMR60YBFNxYCYIiO6z037ZRDiSsonlRyv++pUdEEOuBPHjNKiE3dnuE2zCAvaQ4iM+lUaIUNBOj7a+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:35.745874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06003","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e096df085803e65e356185b870d6840b2f0c2aa2f685ac62a5a0c240e832366","sha256:64396b4660bfed8e25e10f204415b9ed2a65c3d4c5053c651183b3d56914e7f0"],"state_sha256":"148d814dcbe04002506591a14f57898ba68af624de0bad6912e0154e24d7def9"}