{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HGD3E7VSPXOOYJM6QTHNYDJW2B","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":"d3f9813d8499bbb7e801d6739596f9b6aad2e03161ae59171686c788ff9f7e89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-11-04T06:57:04Z","title_canon_sha256":"b68f5a972632b51df05b345e0cc735d38dda4ee94a6efc818eb4e45e9952f263"},"schema_version":"1.0","source":{"id":"2211.02286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02286","created_at":"2026-07-05T05:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02286v1","created_at":"2026-07-05T05:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02286","created_at":"2026-07-05T05:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"HGD3E7VSPXOO","created_at":"2026-07-05T05:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"HGD3E7VSPXOOYJM6","created_at":"2026-07-05T05:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"HGD3E7VS","created_at":"2026-07-05T05:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:28d150ad3bec1844c0572a44c0df444e19f2b6e0987dea0c86714f95dfd48a78","target":"graph","created_at":"2026-07-05T05:13:13Z","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/2211.02286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Martin Maas, Mustafa Uysal, Richard McDougall, Ubaid Ullah Hafeez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-11-04T06:57:04Z","title":"Rethinking Storage Management for Data Processing Pipelines in Cloud Data Centers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02286","kind":"arxiv","version":1},"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:d55bbcc235764f868343a56b899619c8291c65f2d3146a08fe0d6b13bd41bb20","target":"record","created_at":"2026-07-05T05:13:13Z","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":"d3f9813d8499bbb7e801d6739596f9b6aad2e03161ae59171686c788ff9f7e89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-11-04T06:57:04Z","title_canon_sha256":"b68f5a972632b51df05b345e0cc735d38dda4ee94a6efc818eb4e45e9952f263"},"schema_version":"1.0","source":{"id":"2211.02286","kind":"arxiv","version":1}},"canonical_sha256":"3987b27eb27ddcec259e84cedc0d36d04cb5a0e5e351638c70ea68cd24cf1688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3987b27eb27ddcec259e84cedc0d36d04cb5a0e5e351638c70ea68cd24cf1688","first_computed_at":"2026-07-05T05:13:13.669239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:13.669239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WSgknknaGWZtSABoK+o6/B12o3IYT6FG/HauJcktA4H6VeQhwoTg0ULdmPuXhzFtXzxm2uXMXwbkd6Um+aoZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:13.669606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d55bbcc235764f868343a56b899619c8291c65f2d3146a08fe0d6b13bd41bb20","sha256:28d150ad3bec1844c0572a44c0df444e19f2b6e0987dea0c86714f95dfd48a78"],"state_sha256":"7d28c7d336235236575ef552efbe14078b27f5ec838e5c66ccdd8d78b8394508"}