{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UUBPWRM5MTXHJORFKXPTN2IFT7","short_pith_number":"pith:UUBPWRM5","schema_version":"1.0","canonical_sha256":"a502fb459d64ee74ba2555df36e9059fe4880c8ce63bdb99ef2bd8b9bcb919c8","source":{"kind":"arxiv","id":"1807.07724","version":4},"attestation_state":"computed","paper":{"title":"Apache Spark Streaming, Kafka and HarmonicIO: A Performance Benchmark and Architecture Comparison for Enterprise and Scientific Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andreas Hellander, Ben Blamey, Salman Toor","submitted_at":"2018-07-20T07:39:07Z","abstract_excerpt":"This paper presents a benchmark of stream processing throughput comparing Apache Spark Streaming (under file-, TCP socket- and Kafka-based stream integration), with a prototype P2P stream processing framework, HarmonicIO. Maximum throughput for a spectrum of stream processing loads are measured, specifically, those with large message sizes (up to 10MB), and heavy CPU loads -- more typical of scientific computing use cases (such as microscopy), than enterprise contexts. A detailed exploration of the performance characteristics with these streaming sources, under varying loads, reveals an interp"},"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":"1807.07724","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-07-20T07:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"18c4580684db80501441c1cdfe847a8e593de34a1a56503032a1b3c949df7f9e","abstract_canon_sha256":"b219ae69be1fa635f2d80a6a7b6f4b06702acd49fc43dc80dd041ce6d4023419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:13.706342Z","signature_b64":"7lLbb6TFdK0GjzACDkM7J4+um2qdFV4Lws4UF8CCCzQaZtJJs+dAgYJGlRXv9kzXTVmuV0ZYDdsqnpi/ISr5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a502fb459d64ee74ba2555df36e9059fe4880c8ce63bdb99ef2bd8b9bcb919c8","last_reissued_at":"2026-07-05T00:27:13.705845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:13.705845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Apache Spark Streaming, Kafka and HarmonicIO: A Performance Benchmark and Architecture Comparison for Enterprise and Scientific Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andreas Hellander, Ben Blamey, Salman Toor","submitted_at":"2018-07-20T07:39:07Z","abstract_excerpt":"This paper presents a benchmark of stream processing throughput comparing Apache Spark Streaming (under file-, TCP socket- and Kafka-based stream integration), with a prototype P2P stream processing framework, HarmonicIO. Maximum throughput for a spectrum of stream processing loads are measured, specifically, those with large message sizes (up to 10MB), and heavy CPU loads -- more typical of scientific computing use cases (such as microscopy), than enterprise contexts. A detailed exploration of the performance characteristics with these streaming sources, under varying loads, reveals an interp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07724","kind":"arxiv","version":4},"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/1807.07724/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":"1807.07724","created_at":"2026-07-05T00:27:13.705919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.07724v4","created_at":"2026-07-05T00:27:13.705919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07724","created_at":"2026-07-05T00:27:13.705919+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUBPWRM5MTXH","created_at":"2026-07-05T00:27:13.705919+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUBPWRM5MTXHJORF","created_at":"2026-07-05T00:27:13.705919+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUBPWRM5","created_at":"2026-07-05T00:27:13.705919+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/UUBPWRM5MTXHJORFKXPTN2IFT7","json":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7.json","graph_json":"https://pith.science/api/pith-number/UUBPWRM5MTXHJORFKXPTN2IFT7/graph.json","events_json":"https://pith.science/api/pith-number/UUBPWRM5MTXHJORFKXPTN2IFT7/events.json","paper":"https://pith.science/paper/UUBPWRM5"},"agent_actions":{"view_html":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7","download_json":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7.json","view_paper":"https://pith.science/paper/UUBPWRM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.07724&json=true","fetch_graph":"https://pith.science/api/pith-number/UUBPWRM5MTXHJORFKXPTN2IFT7/graph.json","fetch_events":"https://pith.science/api/pith-number/UUBPWRM5MTXHJORFKXPTN2IFT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7/action/storage_attestation","attest_author":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7/action/author_attestation","sign_citation":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7/action/citation_signature","submit_replication":"https://pith.science/pith/UUBPWRM5MTXHJORFKXPTN2IFT7/action/replication_record"}},"created_at":"2026-07-05T00:27:13.705919+00:00","updated_at":"2026-07-05T00:27:13.705919+00:00"}