{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QV7NNRNRM3JWZETJB2MNHBNFDL","short_pith_number":"pith:QV7NNRNR","schema_version":"1.0","canonical_sha256":"857ed6c5b166d36c92690e98d385a51adf595037199bc188d632846fd573ff3c","source":{"kind":"arxiv","id":"2102.11245","version":1},"attestation_state":"computed","paper":{"title":"Silent Data Corruptions at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.AR","authors_text":"Bharath Muthiah, Chris Mason, Harish Dattatraya Dixit, Matt Beadon, Sneha Pendharkar, Sriram Sankar, Tejasvi Chakravarthy","submitted_at":"2021-02-22T18:30:15Z","abstract_excerpt":"Silent Data Corruption (SDC) can have negative impact on large-scale infrastructure services. SDCs are not captured by error reporting mechanisms within a Central Processing Unit (CPU) and hence are not traceable at the hardware level. However, the data corruptions propagate across the stack and manifest as application-level problems. These types of errors can result in data loss and can require months of debug engineering time. In this paper, we describe common defect types observed in silicon manufacturing that leads to SDCs. We discuss a real-world example of silent data corruption within a"},"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":"2102.11245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2021-02-22T18:30:15Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"81f6621702288d6a9088a8a6b0ce784c123650c6bfe554d32a4670e354e2f3bf","abstract_canon_sha256":"c784766f3045bbead87799c525ca460119ccf07995e21e6bc9267a5a1b090cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:05.674552Z","signature_b64":"BQtqGrDpShPX0vjkrSdLqdZHYs5Pfo+yQTMD/vCYQC00G45Pr2P1ijvcc1lzE3UQUb3rShxmnznMTJEHYsGYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"857ed6c5b166d36c92690e98d385a51adf595037199bc188d632846fd573ff3c","last_reissued_at":"2026-07-05T02:17:05.674136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:05.674136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Silent Data Corruptions at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.AR","authors_text":"Bharath Muthiah, Chris Mason, Harish Dattatraya Dixit, Matt Beadon, Sneha Pendharkar, Sriram Sankar, Tejasvi Chakravarthy","submitted_at":"2021-02-22T18:30:15Z","abstract_excerpt":"Silent Data Corruption (SDC) can have negative impact on large-scale infrastructure services. SDCs are not captured by error reporting mechanisms within a Central Processing Unit (CPU) and hence are not traceable at the hardware level. However, the data corruptions propagate across the stack and manifest as application-level problems. These types of errors can result in data loss and can require months of debug engineering time. In this paper, we describe common defect types observed in silicon manufacturing that leads to SDCs. We discuss a real-world example of silent data corruption within a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11245","kind":"arxiv","version":1},"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/2102.11245/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":"2102.11245","created_at":"2026-07-05T02:17:05.674198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11245v1","created_at":"2026-07-05T02:17:05.674198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11245","created_at":"2026-07-05T02:17:05.674198+00:00"},{"alias_kind":"pith_short_12","alias_value":"QV7NNRNRM3JW","created_at":"2026-07-05T02:17:05.674198+00:00"},{"alias_kind":"pith_short_16","alias_value":"QV7NNRNRM3JWZETJ","created_at":"2026-07-05T02:17:05.674198+00:00"},{"alias_kind":"pith_short_8","alias_value":"QV7NNRNR","created_at":"2026-07-05T02:17:05.674198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21791","citing_title":"Single-Event Upsets in 3D Gaussian Splatting Rendering: Bit-Level Criticality, Spatial Extent, and a Parallel Support Guard","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10651","citing_title":"Kwai Keye-VL-2.0 Technical Report","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05433","citing_title":"Zero knowledge verification for frontier AI training is possible","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02430","citing_title":"Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27934","citing_title":"Self-Verifying Measurement Records: Hash-Linked Evidence Graphs for Hardware Benchmarking","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2312.11805","citing_title":"Gemini: A Family of Highly Capable Multimodal Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15638","citing_title":"ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data Corruptions","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07041","citing_title":"AIReSim: A Discrete Event Simulator for Large-scale AI Cluster Reliability Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08594","citing_title":"FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20587","citing_title":"Making TransactionIsolation Checking Practical","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09994","citing_title":"Aging Aware Adaptive Voltage Scaling for Reliable and Efficient AI Accelerators","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09073","citing_title":"DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07417","citing_title":"Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10390","citing_title":"LLM-PRISM: Characterizing Silent Data Corruption from Permanent GPU Faults in LLM Training","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22032","citing_title":"Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04213","citing_title":"The Anatomy of Silent Data Corruption: GPU Error Pattern Study and Modeling Guidance","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL","json":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL.json","graph_json":"https://pith.science/api/pith-number/QV7NNRNRM3JWZETJB2MNHBNFDL/graph.json","events_json":"https://pith.science/api/pith-number/QV7NNRNRM3JWZETJB2MNHBNFDL/events.json","paper":"https://pith.science/paper/QV7NNRNR"},"agent_actions":{"view_html":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL","download_json":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL.json","view_paper":"https://pith.science/paper/QV7NNRNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11245&json=true","fetch_graph":"https://pith.science/api/pith-number/QV7NNRNRM3JWZETJB2MNHBNFDL/graph.json","fetch_events":"https://pith.science/api/pith-number/QV7NNRNRM3JWZETJB2MNHBNFDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL/action/storage_attestation","attest_author":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL/action/author_attestation","sign_citation":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL/action/citation_signature","submit_replication":"https://pith.science/pith/QV7NNRNRM3JWZETJB2MNHBNFDL/action/replication_record"}},"created_at":"2026-07-05T02:17:05.674198+00:00","updated_at":"2026-07-05T02:17:05.674198+00:00"}