{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EUO3PKXRPHPVL4XRDXCBAJDEFX","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":"2056549c61316d06b6544d13a793e99604446839c715ab3698cb860cf795b537","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-07-28T12:29:05Z","title_canon_sha256":"3c41b7356fa4850e78be37e2ba6fcc13e05d54f5b744ee93f713b8a0f5d21217"},"schema_version":"1.0","source":{"id":"2107.13317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.13317","created_at":"2026-07-05T03:36:56Z"},{"alias_kind":"arxiv_version","alias_value":"2107.13317v2","created_at":"2026-07-05T03:36:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13317","created_at":"2026-07-05T03:36:56Z"},{"alias_kind":"pith_short_12","alias_value":"EUO3PKXRPHPV","created_at":"2026-07-05T03:36:56Z"},{"alias_kind":"pith_short_16","alias_value":"EUO3PKXRPHPVL4XR","created_at":"2026-07-05T03:36:56Z"},{"alias_kind":"pith_short_8","alias_value":"EUO3PKXR","created_at":"2026-07-05T03:36:56Z"}],"graph_snapshots":[{"event_id":"sha256:b2cf14b2ba0dba16590cbc1f37a5963ac65b4f5500f98090dbbba897b6315202","target":"graph","created_at":"2026-07-05T03:36:56Z","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/2107.13317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed dataflow systems enable data-parallel processing of large datasets on clusters. Public cloud providers offer a large variety and quantity of resources that can be used for such clusters. Yet, selecting appropriate cloud resources for dataflow jobs - that neither lead to bottlenecks nor to low resource utilization - is often challenging, even for expert users such as data engineers.\n  We present C3O, a collaborative system for optimizing data processing cluster configurations in public clouds based on shared historical runtime data. The shared data is utilized for predicting the run","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":"2021-07-28T12:29:05Z","title":"C3O: Collaborative Cluster Configuration Optimization for Distributed Data Processing in Public Clouds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13317","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:c31a7e2822cf5b58176982ea941b20462afbf28f3c0714a1ab412c48a0d1445b","target":"record","created_at":"2026-07-05T03:36:56Z","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":"2056549c61316d06b6544d13a793e99604446839c715ab3698cb860cf795b537","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-07-28T12:29:05Z","title_canon_sha256":"3c41b7356fa4850e78be37e2ba6fcc13e05d54f5b744ee93f713b8a0f5d21217"},"schema_version":"1.0","source":{"id":"2107.13317","kind":"arxiv","version":2}},"canonical_sha256":"251db7aaf179df55f2f11dc41024642dddd090d2776fd97cf58b34548cd92af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"251db7aaf179df55f2f11dc41024642dddd090d2776fd97cf58b34548cd92af5","first_computed_at":"2026-07-05T03:36:56.276558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:56.276558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j8jD5k6hvI7u0BAedwep4rY/umN4IetADU7Ij6lrbvP8+HQlkIe9aCKraBYgwOKRaw7SzeF2z5MOrmCok38PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:56.277053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.13317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c31a7e2822cf5b58176982ea941b20462afbf28f3c0714a1ab412c48a0d1445b","sha256:b2cf14b2ba0dba16590cbc1f37a5963ac65b4f5500f98090dbbba897b6315202"],"state_sha256":"aa50ab1f32657f9ec9b322ac77f08412b00c974855a1ee417396903cac80fd65"}