{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2TL2IXJBN6LHPJH2R5FSFNBTGC","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":"757c9d65e0625b78df6ba9f6cd2f0cd9f1c3d08165b64e37c12de0fb086e2a73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-26T02:18:53Z","title_canon_sha256":"7c3a56556552138e8549882bd24ae8c1d77b294c62809d6becb53c16e0bcfd62"},"schema_version":"1.0","source":{"id":"2605.26461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26461","created_at":"2026-05-27T01:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26461v1","created_at":"2026-05-27T01:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26461","created_at":"2026-05-27T01:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"2TL2IXJBN6LH","created_at":"2026-05-27T01:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"2TL2IXJBN6LHPJH2","created_at":"2026-05-27T01:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"2TL2IXJB","created_at":"2026-05-27T01:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:7975b0f59b9d3c341e1292aa5aeeee463793a305355d147c0fa24142affdc646","target":"graph","created_at":"2026-05-27T01:05:19Z","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/2605.26461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NVIDIA Multi-Process Service (MPS) enables fine-grained GPU sharing by allowing multiple processes to execute concurrently on the same GPU, making it an important mechanism for improving GPU utilization. However, MPS has weak fault resilience: a fault in one process can terminate all co-running processes, limiting its adoption in resilience-critical settings such as multi-tenant GPU clusters. In this work, we design fault-resilient MPS to solve this problem. Our design is guided by insights from a systematic characterization of GPU faults and a deep analysis of their end-to-end processing pipe","authors_text":"Jiarong Xing, Kaijian Wang, Rixin Liu, Xingqi Cui, Xinheng Ding, Yuke Wang, Zirui Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-26T02:18:53Z","title":"Characterization-Guided GPU Fault Resilience in NVIDIA MPS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26461","kind":"arxiv","version":1},"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":"sha256:7ff58e1e6cc91b3c50e99929ce03b27c8ec584d28efa3a10cc858e9bcc207093","target":"record","created_at":"2026-05-27T01:05:19Z","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":"757c9d65e0625b78df6ba9f6cd2f0cd9f1c3d08165b64e37c12de0fb086e2a73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-26T02:18:53Z","title_canon_sha256":"7c3a56556552138e8549882bd24ae8c1d77b294c62809d6becb53c16e0bcfd62"},"schema_version":"1.0","source":{"id":"2605.26461","kind":"arxiv","version":1}},"canonical_sha256":"d4d7a45d216f9677a4fa8f4b22b43330a4833e792e1f1e03acf87b77bb94e24b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4d7a45d216f9677a4fa8f4b22b43330a4833e792e1f1e03acf87b77bb94e24b","first_computed_at":"2026-05-27T01:05:19.212624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:19.212624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OtX1tuwKU5cjV2WEUuX9k/tNckZrFskv+uUYfE9lS3q7AeHh4//+ntgU7a7CPW+5aVNT1ZJ49Bq0i3PNCgzIBQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:19.213403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ff58e1e6cc91b3c50e99929ce03b27c8ec584d28efa3a10cc858e9bcc207093","sha256:7975b0f59b9d3c341e1292aa5aeeee463793a305355d147c0fa24142affdc646"],"state_sha256":"d43721ac61aa22290724b567cd087d8ae17f4ae3951d0d76861fdddbaeddad38"}