{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Z7XWCDWODZ2JIJIECIRTZSCR3L","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":"062355659c1359f697bea511c5fd837ed82db21c8a27ffc2719af4b6985ecdec","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2019-04-26T12:52:02Z","title_canon_sha256":"1d8b176defe683602fe37f72478ca40729d5e6c6307e9a9c843bb66d3efa07b5"},"schema_version":"1.0","source":{"id":"1904.11812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11812","created_at":"2026-07-05T00:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11812v2","created_at":"2026-07-05T00:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11812","created_at":"2026-07-05T00:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z7XWCDWODZ2J","created_at":"2026-07-05T00:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z7XWCDWODZ2JIJIE","created_at":"2026-07-05T00:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z7XWCDWO","created_at":"2026-07-05T00:07:51Z"}],"graph_snapshots":[{"event_id":"sha256:5bf9f4ea276a6d6f58127ef09ee1b2ddecbdcac868c5b2db1411a93db25c9257","target":"graph","created_at":"2026-07-05T00:07:51Z","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/1904.11812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As dataset sizes increase, data analysis tasks in high performance computing (HPC) are increasingly dependent on sophisticated dataflows and out-of-core methods for efficient system utilization. In addition, as HPC systems grow, memory access and data sharing are becoming performance bottlenecks. Cloud computing employs a data processing paradigm typically built on a loosely connected group of low-cost computing nodes without relying upon shared storage and/or memory. Apache Spark is a popular engine for large-scale data analysis in the cloud, which we have successfully deployed via job submis","authors_text":"Cameron Christensen, Fran\\c{c}ois Tessier, George K. Thiruvathukal, Venkatram Vishwanath, Xiaoyong Jin","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2019-04-26T12:52:02Z","title":"A Benchmarking Study to Evaluate Apache Spark on Large-Scale Supercomputers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11812","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":"sha256:76bef737cecc1511b5ca7923150d74a0f2bd140159d7f0e98d308831e6627418","target":"record","created_at":"2026-07-05T00:07:51Z","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":"062355659c1359f697bea511c5fd837ed82db21c8a27ffc2719af4b6985ecdec","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2019-04-26T12:52:02Z","title_canon_sha256":"1d8b176defe683602fe37f72478ca40729d5e6c6307e9a9c843bb66d3efa07b5"},"schema_version":"1.0","source":{"id":"1904.11812","kind":"arxiv","version":2}},"canonical_sha256":"cfef610ece1e7494250412233cc851dac0763c92cd84aaf01ae4f94b6a98bf8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfef610ece1e7494250412233cc851dac0763c92cd84aaf01ae4f94b6a98bf8b","first_computed_at":"2026-07-05T00:07:51.575979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:51.575979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bKoEzqIDtO6pbWfKw1BSLEsHEuKVwKgxDKXBlYtKtq7PEt+J8RpuaNEUrfSjzcJjYwnBR1iGtkr10aWSmf2KAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:51.576414Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76bef737cecc1511b5ca7923150d74a0f2bd140159d7f0e98d308831e6627418","sha256:5bf9f4ea276a6d6f58127ef09ee1b2ddecbdcac868c5b2db1411a93db25c9257"],"state_sha256":"8eeda7e97e5b9de0375b8ce141bb6286c461534ce4bdfb362bf4d81a3add4ef7"}