{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z7XWCDWODZ2JIJIECIRTZSCR3L","short_pith_number":"pith:Z7XWCDWO","schema_version":"1.0","canonical_sha256":"cfef610ece1e7494250412233cc851dac0763c92cd84aaf01ae4f94b6a98bf8b","source":{"kind":"arxiv","id":"1904.11812","version":2},"attestation_state":"computed","paper":{"title":"A Benchmarking Study to Evaluate Apache Spark on Large-Scale Supercomputers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.DC","authors_text":"Cameron Christensen, Fran\\c{c}ois Tessier, George K. Thiruvathukal, Venkatram Vishwanath, Xiaoyong Jin","submitted_at":"2019-04-26T12:52:02Z","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"},"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":"1904.11812","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2019-04-26T12:52:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"1d8b176defe683602fe37f72478ca40729d5e6c6307e9a9c843bb66d3efa07b5","abstract_canon_sha256":"062355659c1359f697bea511c5fd837ed82db21c8a27ffc2719af4b6985ecdec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:51.576414Z","signature_b64":"bKoEzqIDtO6pbWfKw1BSLEsHEuKVwKgxDKXBlYtKtq7PEt+J8RpuaNEUrfSjzcJjYwnBR1iGtkr10aWSmf2KAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfef610ece1e7494250412233cc851dac0763c92cd84aaf01ae4f94b6a98bf8b","last_reissued_at":"2026-07-05T00:07:51.575979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:51.575979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Benchmarking Study to Evaluate Apache Spark on Large-Scale Supercomputers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.DC","authors_text":"Cameron Christensen, Fran\\c{c}ois Tessier, George K. Thiruvathukal, Venkatram Vishwanath, Xiaoyong Jin","submitted_at":"2019-04-26T12:52:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11812","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/1904.11812/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":"1904.11812","created_at":"2026-07-05T00:07:51.576036+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11812v2","created_at":"2026-07-05T00:07:51.576036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11812","created_at":"2026-07-05T00:07:51.576036+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7XWCDWODZ2J","created_at":"2026-07-05T00:07:51.576036+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7XWCDWODZ2JIJIE","created_at":"2026-07-05T00:07:51.576036+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7XWCDWO","created_at":"2026-07-05T00:07:51.576036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L","json":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L.json","graph_json":"https://pith.science/api/pith-number/Z7XWCDWODZ2JIJIECIRTZSCR3L/graph.json","events_json":"https://pith.science/api/pith-number/Z7XWCDWODZ2JIJIECIRTZSCR3L/events.json","paper":"https://pith.science/paper/Z7XWCDWO"},"agent_actions":{"view_html":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L","download_json":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L.json","view_paper":"https://pith.science/paper/Z7XWCDWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11812&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7XWCDWODZ2JIJIECIRTZSCR3L/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7XWCDWODZ2JIJIECIRTZSCR3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L/action/storage_attestation","attest_author":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L/action/author_attestation","sign_citation":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L/action/citation_signature","submit_replication":"https://pith.science/pith/Z7XWCDWODZ2JIJIECIRTZSCR3L/action/replication_record"}},"created_at":"2026-07-05T00:07:51.576036+00:00","updated_at":"2026-07-05T00:07:51.576036+00:00"}