{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SYBOYR67IKQMY3SVNZPMFALI2Z","short_pith_number":"pith:SYBOYR67","schema_version":"1.0","canonical_sha256":"9602ec47df42a0cc6e556e5ec28168d6445095fabaf375baa3f407c72459b484","source":{"kind":"arxiv","id":"1604.08484","version":1},"attestation_state":"computed","paper":{"title":"Architectural Impact on Performance of In-memory Data Analytics: Apache Spark Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.PF"],"primary_cat":"cs.DC","authors_text":"Ahsan Javed Awan, Eduard Ayguade, Mats Brorsson, Vladimir Vlassov","submitted_at":"2016-04-28T16:00:38Z","abstract_excerpt":"While cluster computing frameworks are continuously evolving to provide real-time data analysis capabilities, Apache Spark has managed to be at the forefront of big data analytics for being a unified framework for both, batch and stream data processing. However, recent studies on micro-architectural characterization of in-memory data analytics are limited to only batch processing workloads. We compare micro-architectural performance of batch processing and stream processing workloads in Apache Spark using hardware performance counters on a dual socket server. In our evaluation experiments, we "},"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":"1604.08484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-04-28T16:00:38Z","cross_cats_sorted":["cs.AR","cs.PF"],"title_canon_sha256":"330f5f43b63a12b6f3df0d190ea4e87074db728be5a97503f96765c59bfed1b9","abstract_canon_sha256":"7ba392f44051b77c6fdffa2acbe9babe2f3247f338e42bc55e5c42e0bcf72295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:03.846784Z","signature_b64":"dYJiOF21SA8FUp0ctK66SR1ikhXNMfgvXdauUbeteW23j5/oGpUhBLTYh6Zcc6o/94491aKLPjM27ue8DH0zCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9602ec47df42a0cc6e556e5ec28168d6445095fabaf375baa3f407c72459b484","last_reissued_at":"2026-05-18T01:16:03.845912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:03.845912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Architectural Impact on Performance of In-memory Data Analytics: Apache Spark Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.PF"],"primary_cat":"cs.DC","authors_text":"Ahsan Javed Awan, Eduard Ayguade, Mats Brorsson, Vladimir Vlassov","submitted_at":"2016-04-28T16:00:38Z","abstract_excerpt":"While cluster computing frameworks are continuously evolving to provide real-time data analysis capabilities, Apache Spark has managed to be at the forefront of big data analytics for being a unified framework for both, batch and stream data processing. However, recent studies on micro-architectural characterization of in-memory data analytics are limited to only batch processing workloads. We compare micro-architectural performance of batch processing and stream processing workloads in Apache Spark using hardware performance counters on a dual socket server. In our evaluation experiments, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.08484","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":""},"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":"1604.08484","created_at":"2026-05-18T01:16:03.846059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.08484v1","created_at":"2026-05-18T01:16:03.846059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.08484","created_at":"2026-05-18T01:16:03.846059+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYBOYR67IKQM","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYBOYR67IKQMY3SV","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYBOYR67","created_at":"2026-05-18T12:30:44.179134+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/SYBOYR67IKQMY3SVNZPMFALI2Z","json":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z.json","graph_json":"https://pith.science/api/pith-number/SYBOYR67IKQMY3SVNZPMFALI2Z/graph.json","events_json":"https://pith.science/api/pith-number/SYBOYR67IKQMY3SVNZPMFALI2Z/events.json","paper":"https://pith.science/paper/SYBOYR67"},"agent_actions":{"view_html":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z","download_json":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z.json","view_paper":"https://pith.science/paper/SYBOYR67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.08484&json=true","fetch_graph":"https://pith.science/api/pith-number/SYBOYR67IKQMY3SVNZPMFALI2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/SYBOYR67IKQMY3SVNZPMFALI2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z/action/storage_attestation","attest_author":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z/action/author_attestation","sign_citation":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z/action/citation_signature","submit_replication":"https://pith.science/pith/SYBOYR67IKQMY3SVNZPMFALI2Z/action/replication_record"}},"created_at":"2026-05-18T01:16:03.846059+00:00","updated_at":"2026-05-18T01:16:03.846059+00:00"}