{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3RRWU6KQSBXOMEZQGJ3LRR4KYI","short_pith_number":"pith:3RRWU6KQ","canonical_record":{"source":{"id":"2603.00357","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-27T22:44:27Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"e17c98c5444df957bb2aa512f5db7bec9cce37dfcc698d046ebfd3708e446924","abstract_canon_sha256":"591c82626066f63463d2872224c87139169e87f0878f86a7ed77ed07b92d6bc9"},"schema_version":"1.0"},"canonical_sha256":"dc636a7950906ee613303276b8c78ac20be41794b807aa5a16758159a3ab7e78","source":{"kind":"arxiv","id":"2603.00357","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00357","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00357v2","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00357","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"3RRWU6KQSBXO","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"3RRWU6KQSBXOMEZQ","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"3RRWU6KQ","created_at":"2026-05-20T00:01:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3RRWU6KQSBXOMEZQGJ3LRR4KYI","target":"record","payload":{"canonical_record":{"source":{"id":"2603.00357","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-27T22:44:27Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"e17c98c5444df957bb2aa512f5db7bec9cce37dfcc698d046ebfd3708e446924","abstract_canon_sha256":"591c82626066f63463d2872224c87139169e87f0878f86a7ed77ed07b92d6bc9"},"schema_version":"1.0"},"canonical_sha256":"dc636a7950906ee613303276b8c78ac20be41794b807aa5a16758159a3ab7e78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:39.986199Z","signature_b64":"ViIuFnujlwC0ktunb47Rp0/S3nLieLQx0zI1f/oILX19DzLFjlR0Z5rcf0bLSSE9/OogW5qpF7ProXMKzG6mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc636a7950906ee613303276b8c78ac20be41794b807aa5a16758159a3ab7e78","last_reissued_at":"2026-05-20T00:01:39.985415Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:39.985415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.00357","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ek7kWMDWXCHoP731SmvJ9C4JWsHjozExX/Ckbb7M684KOGt/Uo5AjA7vSqiX/XXiCNQIY1HEKM4FsJTY88xyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T13:35:43.675361Z"},"content_sha256":"d19d4924bf5848c93df57f168a313d2a3861a5ab2c26e0b3b2ab2bc4b8d627b6","schema_version":"1.0","event_id":"sha256:d19d4924bf5848c93df57f168a313d2a3861a5ab2c26e0b3b2ab2bc4b8d627b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3RRWU6KQSBXOMEZQGJ3LRR4KYI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.DC","authors_text":"Bogdan Nicolae, Franck Cappello, Jin Lee, Robert Underwood, Sheng Di, Xiaoyi Lu, Xuhang He, Zheng Zhang, Zhonghao Chen","submitted_at":"2026-02-27T22:44:27Z","abstract_excerpt":"In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for this restart-dominant regime. To address this challenge, we propose SPARe - Stacked Parallelism with Adaptive Reordering - a fault-tolerance framework that masks node failures during gradient synchronization by stacking redundant data shards across parallelism groups and adaptively reordering execution. SPARe achieves availability comparable to traditional rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00357","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/2603.00357/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vuq3kMUXkfyxzX7T17ZPil7OxH6ysSkXtJc1MefDR+Z24BbNy9Za2zEF3Rh3GbIRVREVcmyuJ3Du1nHscIqxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T13:35:43.676002Z"},"content_sha256":"fb1e2fc93a96d12a5a69e6a5828249e24be1aff7e1b1e0170cb3590e5366a009","schema_version":"1.0","event_id":"sha256:fb1e2fc93a96d12a5a69e6a5828249e24be1aff7e1b1e0170cb3590e5366a009"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/bundle.json","state_url":"https://pith.science/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T13:35:43Z","links":{"resolver":"https://pith.science/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI","bundle":"https://pith.science/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/bundle.json","state":"https://pith.science/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RRWU6KQSBXOMEZQGJ3LRR4KYI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3RRWU6KQSBXOMEZQGJ3LRR4KYI","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":"591c82626066f63463d2872224c87139169e87f0878f86a7ed77ed07b92d6bc9","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-27T22:44:27Z","title_canon_sha256":"e17c98c5444df957bb2aa512f5db7bec9cce37dfcc698d046ebfd3708e446924"},"schema_version":"1.0","source":{"id":"2603.00357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00357","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00357v2","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00357","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"3RRWU6KQSBXO","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"3RRWU6KQSBXOMEZQ","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"3RRWU6KQ","created_at":"2026-05-20T00:01:39Z"}],"graph_snapshots":[{"event_id":"sha256:fb1e2fc93a96d12a5a69e6a5828249e24be1aff7e1b1e0170cb3590e5366a009","target":"graph","created_at":"2026-05-20T00:01:39Z","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/2603.00357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for this restart-dominant regime. To address this challenge, we propose SPARe - Stacked Parallelism with Adaptive Reordering - a fault-tolerance framework that masks node failures during gradient synchronization by stacking redundant data shards across parallelism groups and adaptively reordering execution. SPARe achieves availability comparable to traditional rep","authors_text":"Bogdan Nicolae, Franck Cappello, Jin Lee, Robert Underwood, Sheng Di, Xiaoyi Lu, Xuhang He, Zheng Zhang, Zhonghao Chen","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-27T22:44:27Z","title":"SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00357","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:d19d4924bf5848c93df57f168a313d2a3861a5ab2c26e0b3b2ab2bc4b8d627b6","target":"record","created_at":"2026-05-20T00:01:39Z","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":"591c82626066f63463d2872224c87139169e87f0878f86a7ed77ed07b92d6bc9","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-27T22:44:27Z","title_canon_sha256":"e17c98c5444df957bb2aa512f5db7bec9cce37dfcc698d046ebfd3708e446924"},"schema_version":"1.0","source":{"id":"2603.00357","kind":"arxiv","version":2}},"canonical_sha256":"dc636a7950906ee613303276b8c78ac20be41794b807aa5a16758159a3ab7e78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc636a7950906ee613303276b8c78ac20be41794b807aa5a16758159a3ab7e78","first_computed_at":"2026-05-20T00:01:39.985415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:39.985415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ViIuFnujlwC0ktunb47Rp0/S3nLieLQx0zI1f/oILX19DzLFjlR0Z5rcf0bLSSE9/OogW5qpF7ProXMKzG6mAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:39.986199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d19d4924bf5848c93df57f168a313d2a3861a5ab2c26e0b3b2ab2bc4b8d627b6","sha256:fb1e2fc93a96d12a5a69e6a5828249e24be1aff7e1b1e0170cb3590e5366a009"],"state_sha256":"464bf4b599b431a98c513de66d9145ef7c1200adb61723fa3cbdff04f60873f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GfKzO/EeDok3OEGF51OxsBcyizxFUBuQGUuEBYGlSZ1NeTaJhw8sJw6VNf/wQ9APatxHXOkjolsn61zsy7P4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T13:35:43.679746Z","bundle_sha256":"fec4af081769696f4a147f9c1d7aa5ed069e27cb1f243083ec1603436e2c9009"}}