{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XRFWWE3C622GTKOVWPOZ7VPTAO","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":"8eb26b91b1fa4b96103f9e3ce66da87e376a43758bd67be96d24b6027004c62c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-01T12:08:48Z","title_canon_sha256":"ee88bf974f0d3061ba65acb84e29e77ef55adbe00665dfe1f092de953de840fa"},"schema_version":"1.0","source":{"id":"2206.00429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00429","created_at":"2026-07-05T04:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00429v1","created_at":"2026-07-05T04:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00429","created_at":"2026-07-05T04:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"XRFWWE3C622G","created_at":"2026-07-05T04:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"XRFWWE3C622GTKOV","created_at":"2026-07-05T04:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"XRFWWE3C","created_at":"2026-07-05T04:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:23e1531cbacfc5a26ee98f1f7951077774f7864a419d4766c9d86f9a0b32079a","target":"graph","created_at":"2026-07-05T04:28:16Z","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/2206.00429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many organizations routinely analyze large datasets using systems for distributed data-parallel processing and clusters of commodity resources. Yet, users need to configure adequate resources for their data processing jobs. This requires significant insights into expected job runtimes and scaling behavior, resource characteristics, input data distributions, and other factors. Unable to estimate performance accurately, users frequently overprovision resources for their jobs, leading to low resource utilization and high costs. In this paper, we present major building blocks towards a collaborati","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-01T12:08:48Z","title":"Collaborative Cluster Configuration for Distributed Data-Parallel Processing: A Research Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00429","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:b985befe4f700deb6a788e94f1c8d2f31280a6855a64c42b008e7bf1fccb85c3","target":"record","created_at":"2026-07-05T04:28:16Z","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":"8eb26b91b1fa4b96103f9e3ce66da87e376a43758bd67be96d24b6027004c62c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-01T12:08:48Z","title_canon_sha256":"ee88bf974f0d3061ba65acb84e29e77ef55adbe00665dfe1f092de953de840fa"},"schema_version":"1.0","source":{"id":"2206.00429","kind":"arxiv","version":1}},"canonical_sha256":"bc4b6b1362f6b469a9d5b3dd9fd5f303b5a0a7175ec86dbc8cec550fa4e74f6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc4b6b1362f6b469a9d5b3dd9fd5f303b5a0a7175ec86dbc8cec550fa4e74f6a","first_computed_at":"2026-07-05T04:28:16.625487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:16.625487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+bcZOTYbbrUb27XpXzJ1qj8mqxpgevjohtZm3cx8g49KF5qvlIhxL3ZZMNytNzPFjLz9JpBYJSxXFak9znpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:16.626009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b985befe4f700deb6a788e94f1c8d2f31280a6855a64c42b008e7bf1fccb85c3","sha256:23e1531cbacfc5a26ee98f1f7951077774f7864a419d4766c9d86f9a0b32079a"],"state_sha256":"398ff6864ad897588659da0b2e1ba075109ed961e4b87c3acdcbb5a1e4fb72b8"}