{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YHDOHWQM6C335YM3GDILUX72W2","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":"a58573e55c46fb317bb40453343e1285d474616a73fb203175368c11e469b8cd","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-06-06T13:37:18Z","title_canon_sha256":"7c397ee694a74fa91bf23a44dd50f2d1ef285b2c7d5c55760d46f0391d3ac9c8"},"schema_version":"1.0","source":{"id":"2306.03672","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03672","created_at":"2026-07-05T06:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03672v2","created_at":"2026-07-05T06:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03672","created_at":"2026-07-05T06:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"YHDOHWQM6C33","created_at":"2026-07-05T06:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"YHDOHWQM6C335YM3","created_at":"2026-07-05T06:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"YHDOHWQM","created_at":"2026-07-05T06:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:814d8266a1e725054187ada5adf46779267d9087701df2c4435407e95f6dd9fb","target":"graph","created_at":"2026-07-05T06:18:23Z","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/2306.03672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed dataflow systems such as Apache Spark or Apache Flink enable parallel, in-memory data processing on large clusters of commodity hardware. Consequently, the appropriate amount of memory to allocate to the cluster is a crucial consideration.\n  In this paper, we analyze the challenge of efficient resource allocation for distributed data processing, focusing on memory. We emphasize that in-memory processing with in-memory data processing frameworks can undermine resource efficiency. Based on the findings of our trace data analysis, we compile requirements towards an automated solution ","authors_text":"Dominik Scheinert, Jonathan Will, Lauritz Thamsen, Odej Kao","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-06-06T13:37:18Z","title":"Selecting Efficient Cluster Resources for Data Analytics: When and How to Allocate for In-Memory Processing?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03672","kind":"arxiv","version":2},"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:c7a6ac607c68a345a9b88455d290d6c5d16e65a1d0c4837946f7a823a2c84579","target":"record","created_at":"2026-07-05T06:18:23Z","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":"a58573e55c46fb317bb40453343e1285d474616a73fb203175368c11e469b8cd","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-06-06T13:37:18Z","title_canon_sha256":"7c397ee694a74fa91bf23a44dd50f2d1ef285b2c7d5c55760d46f0391d3ac9c8"},"schema_version":"1.0","source":{"id":"2306.03672","kind":"arxiv","version":2}},"canonical_sha256":"c1c6e3da0cf0b7bee19b30d0ba5ffab69e42958ad5ea7bbef72f0d23fb2f6fa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1c6e3da0cf0b7bee19b30d0ba5ffab69e42958ad5ea7bbef72f0d23fb2f6fa0","first_computed_at":"2026-07-05T06:18:23.575701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:23.575701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e8XmIY24lYKpVHzAGqVuvtp9u0H/wfcKY5sLOng3HPUT/J8bmDRFDUXnAnz7U+ppwy8SUhSQr5c+wmlzybW3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:23.576453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03672","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7a6ac607c68a345a9b88455d290d6c5d16e65a1d0c4837946f7a823a2c84579","sha256:814d8266a1e725054187ada5adf46779267d9087701df2c4435407e95f6dd9fb"],"state_sha256":"799a52d9c2d43062f983329ebef58ade108d1a3b12de520dfaf50af344b32e8f"}