{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EUO3PKXRPHPVL4XRDXCBAJDEFX","short_pith_number":"pith:EUO3PKXR","schema_version":"1.0","canonical_sha256":"251db7aaf179df55f2f11dc41024642dddd090d2776fd97cf58b34548cd92af5","source":{"kind":"arxiv","id":"2107.13317","version":2},"attestation_state":"computed","paper":{"title":"C3O: Collaborative Cluster Configuration Optimization for Distributed Data Processing in Public Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","submitted_at":"2021-07-28T12:29:05Z","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"},"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":"2107.13317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-07-28T12:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"3c41b7356fa4850e78be37e2ba6fcc13e05d54f5b744ee93f713b8a0f5d21217","abstract_canon_sha256":"2056549c61316d06b6544d13a793e99604446839c715ab3698cb860cf795b537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:56.277053Z","signature_b64":"j8jD5k6hvI7u0BAedwep4rY/umN4IetADU7Ij6lrbvP8+HQlkIe9aCKraBYgwOKRaw7SzeF2z5MOrmCok38PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"251db7aaf179df55f2f11dc41024642dddd090d2776fd97cf58b34548cd92af5","last_reissued_at":"2026-07-05T03:36:56.276558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:56.276558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C3O: Collaborative Cluster Configuration Optimization for Distributed Data Processing in Public Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","submitted_at":"2021-07-28T12:29:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13317","kind":"arxiv","version":2},"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/2107.13317/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":"2107.13317","created_at":"2026-07-05T03:36:56.276620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13317v2","created_at":"2026-07-05T03:36:56.276620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13317","created_at":"2026-07-05T03:36:56.276620+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUO3PKXRPHPV","created_at":"2026-07-05T03:36:56.276620+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUO3PKXRPHPVL4XR","created_at":"2026-07-05T03:36:56.276620+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUO3PKXR","created_at":"2026-07-05T03:36:56.276620+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/EUO3PKXRPHPVL4XRDXCBAJDEFX","json":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX.json","graph_json":"https://pith.science/api/pith-number/EUO3PKXRPHPVL4XRDXCBAJDEFX/graph.json","events_json":"https://pith.science/api/pith-number/EUO3PKXRPHPVL4XRDXCBAJDEFX/events.json","paper":"https://pith.science/paper/EUO3PKXR"},"agent_actions":{"view_html":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX","download_json":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX.json","view_paper":"https://pith.science/paper/EUO3PKXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13317&json=true","fetch_graph":"https://pith.science/api/pith-number/EUO3PKXRPHPVL4XRDXCBAJDEFX/graph.json","fetch_events":"https://pith.science/api/pith-number/EUO3PKXRPHPVL4XRDXCBAJDEFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX/action/storage_attestation","attest_author":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX/action/author_attestation","sign_citation":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX/action/citation_signature","submit_replication":"https://pith.science/pith/EUO3PKXRPHPVL4XRDXCBAJDEFX/action/replication_record"}},"created_at":"2026-07-05T03:36:56.276620+00:00","updated_at":"2026-07-05T03:36:56.276620+00:00"}