{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HGD3E7VSPXOOYJM6QTHNYDJW2B","short_pith_number":"pith:HGD3E7VS","schema_version":"1.0","canonical_sha256":"3987b27eb27ddcec259e84cedc0d36d04cb5a0e5e351638c70ea68cd24cf1688","source":{"kind":"arxiv","id":"2211.02286","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Storage Management for Data Processing Pipelines in Cloud Data Centers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Martin Maas, Mustafa Uysal, Richard McDougall, Ubaid Ullah Hafeez","submitted_at":"2022-11-04T06:57:04Z","abstract_excerpt":"Data processing frameworks such as Apache Beam and Apache Spark are used for a wide range of applications, from logs analysis to data preparation for DNN training. It is thus unsurprising that there has been a large amount of work on optimizing these frameworks, including their storage management. The shift to cloud computing requires optimization across all pipelines concurrently running across a cluster. In this paper, we look at one specific instance of this problem: placement of I/O-intensive temporary intermediate data on SSD and HDD. Efficient data placement is challenging since I/O dens"},"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":"2211.02286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-11-04T06:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"b68f5a972632b51df05b345e0cc735d38dda4ee94a6efc818eb4e45e9952f263","abstract_canon_sha256":"d3f9813d8499bbb7e801d6739596f9b6aad2e03161ae59171686c788ff9f7e89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:13.669606Z","signature_b64":"WSgknknaGWZtSABoK+o6/B12o3IYT6FG/HauJcktA4H6VeQhwoTg0ULdmPuXhzFtXzxm2uXMXwbkd6Um+aoZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3987b27eb27ddcec259e84cedc0d36d04cb5a0e5e351638c70ea68cd24cf1688","last_reissued_at":"2026-07-05T05:13:13.669239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:13.669239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Storage Management for Data Processing Pipelines in Cloud Data Centers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Martin Maas, Mustafa Uysal, Richard McDougall, Ubaid Ullah Hafeez","submitted_at":"2022-11-04T06:57:04Z","abstract_excerpt":"Data processing frameworks such as Apache Beam and Apache Spark are used for a wide range of applications, from logs analysis to data preparation for DNN training. It is thus unsurprising that there has been a large amount of work on optimizing these frameworks, including their storage management. The shift to cloud computing requires optimization across all pipelines concurrently running across a cluster. In this paper, we look at one specific instance of this problem: placement of I/O-intensive temporary intermediate data on SSD and HDD. Efficient data placement is challenging since I/O dens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02286","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/2211.02286/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":"2211.02286","created_at":"2026-07-05T05:13:13.669300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02286v1","created_at":"2026-07-05T05:13:13.669300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02286","created_at":"2026-07-05T05:13:13.669300+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGD3E7VSPXOO","created_at":"2026-07-05T05:13:13.669300+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGD3E7VSPXOOYJM6","created_at":"2026-07-05T05:13:13.669300+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGD3E7VS","created_at":"2026-07-05T05:13:13.669300+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/HGD3E7VSPXOOYJM6QTHNYDJW2B","json":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B.json","graph_json":"https://pith.science/api/pith-number/HGD3E7VSPXOOYJM6QTHNYDJW2B/graph.json","events_json":"https://pith.science/api/pith-number/HGD3E7VSPXOOYJM6QTHNYDJW2B/events.json","paper":"https://pith.science/paper/HGD3E7VS"},"agent_actions":{"view_html":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B","download_json":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B.json","view_paper":"https://pith.science/paper/HGD3E7VS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02286&json=true","fetch_graph":"https://pith.science/api/pith-number/HGD3E7VSPXOOYJM6QTHNYDJW2B/graph.json","fetch_events":"https://pith.science/api/pith-number/HGD3E7VSPXOOYJM6QTHNYDJW2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B/action/storage_attestation","attest_author":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B/action/author_attestation","sign_citation":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B/action/citation_signature","submit_replication":"https://pith.science/pith/HGD3E7VSPXOOYJM6QTHNYDJW2B/action/replication_record"}},"created_at":"2026-07-05T05:13:13.669300+00:00","updated_at":"2026-07-05T05:13:13.669300+00:00"}