{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SVQDZ3RWBF6P5ZMVXFHBHKKMRE","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":"70211e7945f4ee7dff53fde7f2c5d47973861633ff482690ed8a85155b41e757","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-05-19T07:52:17Z","title_canon_sha256":"d1f3c90fd53f02e15d77c57af1c41356f1ee50ced82f399d0e7edfd762709f9b"},"schema_version":"1.0","source":{"id":"2505.12815","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12815","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12815v2","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12815","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"SVQDZ3RWBF6P","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_16","alias_value":"SVQDZ3RWBF6P5ZMV","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_8","alias_value":"SVQDZ3RW","created_at":"2026-07-05T12:11:17Z"}],"graph_snapshots":[{"event_id":"sha256:62d15062ae6a9685fdfa3575997c66895f2f5aa73f7cee91f511a03413845a6c","target":"graph","created_at":"2026-07-05T12:11:17Z","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/2505.12815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Node and link churn in multi-party, cross-region clusters over wide-area networks (WANs) often disrupts distributed training. However, checkpoint-based recovery and cloud-centric autoscaling react slowly and assume centralized control, which is misaligned with the self-governed setup where institutions can freely join and leave. This paper proposes Chaos, a multi-party distributed training system with self-healing and autoscaling, enabling robust and elastic training under churn. It speeds up autoscaling via multi-neighbor state replication and model sharding. We formalize the sharding and ass","authors_text":"Gang Sun, Hongfang Yu, Long Luo, Mohsen Guizani, Qirong Ho, Rongxing Xiao, Steve Liu, Wenjiao Feng, Zonghang Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-05-19T07:52:17Z","title":"Learning In Chaos: Efficient Autoscaling and Self-Healing for Multi-Party Distributed Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12815","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":"sha256:2020d6629c203072af50260eda120aac94e77462876bad477c83de763e477c42","target":"record","created_at":"2026-07-05T12:11:17Z","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":"70211e7945f4ee7dff53fde7f2c5d47973861633ff482690ed8a85155b41e757","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-05-19T07:52:17Z","title_canon_sha256":"d1f3c90fd53f02e15d77c57af1c41356f1ee50ced82f399d0e7edfd762709f9b"},"schema_version":"1.0","source":{"id":"2505.12815","kind":"arxiv","version":2}},"canonical_sha256":"95603cee36097cfee595b94e13a94c89009bd31445b446107b446297746de5c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95603cee36097cfee595b94e13a94c89009bd31445b446107b446297746de5c6","first_computed_at":"2026-07-05T12:11:17.976725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:17.976725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WKX0WYU8TQBxlvRZ650CuyDQS6Ysdn+gzFcoiB9KqmmEHVx7FyfVNEkUeWQ38p87f/FFpVk2lx5QJOeHBBI8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:17.977281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12815","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2020d6629c203072af50260eda120aac94e77462876bad477c83de763e477c42","sha256:62d15062ae6a9685fdfa3575997c66895f2f5aa73f7cee91f511a03413845a6c"],"state_sha256":"a24194383f0e058060f4a551427156ff0a7764c96a27d2f5fe0a697134abfa2d"}