{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TONNF7SQXQB4JE6RGONWKVXHKC","short_pith_number":"pith:TONNF7SQ","schema_version":"1.0","canonical_sha256":"9b9ad2fe50bc03c493d1339b6556e7509f56a8d8b6520c949af9a9fd593cecd7","source":{"kind":"arxiv","id":"2309.00269","version":2},"attestation_state":"computed","paper":{"title":"Co-Tuning of Cloud Infrastructure and Distributed Data Processing Platforms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Faheem Ullah, Isuru Dharmadasa","submitted_at":"2023-09-01T06:00:46Z","abstract_excerpt":"Distributed Data Processing Platforms (e.g., Hadoop, Spark, and Flink) are widely used to store and process data in a cloud environment. These platforms distribute the storage and processing of data among the computing nodes of a cloud. The efficient use of these platforms requires users to (i) configure the cloud i.e., determine the number and type of computing nodes, and (ii) tune the configuration parameters (e.g., data replication factor) of the platform. However, both these tasks require in-depth knowledge of the cloud infrastructure and distributed data processing platforms. Therefore, i"},"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":"2309.00269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-09-01T06:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"67db4e628c38190bb1e91bf96e835056e93e48f585a63f65349b2c0f9e7fc93c","abstract_canon_sha256":"addd59997209a8f730791ccaa1795c8e4949d50ca6c328efbf47b5ccaae17f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:11.814187Z","signature_b64":"jROf/bjm6T+Is96UmXd6cG8JuvdKG0BOl/Jpx/DH5BZMkTztcCu4b7Hcoba4cdTp35nMMiybvN5DsEFqdSR2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b9ad2fe50bc03c493d1339b6556e7509f56a8d8b6520c949af9a9fd593cecd7","last_reissued_at":"2026-07-05T07:21:11.813700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:11.813700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-Tuning of Cloud Infrastructure and Distributed Data Processing Platforms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Faheem Ullah, Isuru Dharmadasa","submitted_at":"2023-09-01T06:00:46Z","abstract_excerpt":"Distributed Data Processing Platforms (e.g., Hadoop, Spark, and Flink) are widely used to store and process data in a cloud environment. These platforms distribute the storage and processing of data among the computing nodes of a cloud. The efficient use of these platforms requires users to (i) configure the cloud i.e., determine the number and type of computing nodes, and (ii) tune the configuration parameters (e.g., data replication factor) of the platform. However, both these tasks require in-depth knowledge of the cloud infrastructure and distributed data processing platforms. Therefore, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00269","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/2309.00269/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":"2309.00269","created_at":"2026-07-05T07:21:11.813757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00269v2","created_at":"2026-07-05T07:21:11.813757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00269","created_at":"2026-07-05T07:21:11.813757+00:00"},{"alias_kind":"pith_short_12","alias_value":"TONNF7SQXQB4","created_at":"2026-07-05T07:21:11.813757+00:00"},{"alias_kind":"pith_short_16","alias_value":"TONNF7SQXQB4JE6R","created_at":"2026-07-05T07:21:11.813757+00:00"},{"alias_kind":"pith_short_8","alias_value":"TONNF7SQ","created_at":"2026-07-05T07:21:11.813757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08715","citing_title":"Balancing Fixed Number of Nodes Among Multiple Fixed Clusters","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC","json":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC.json","graph_json":"https://pith.science/api/pith-number/TONNF7SQXQB4JE6RGONWKVXHKC/graph.json","events_json":"https://pith.science/api/pith-number/TONNF7SQXQB4JE6RGONWKVXHKC/events.json","paper":"https://pith.science/paper/TONNF7SQ"},"agent_actions":{"view_html":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC","download_json":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC.json","view_paper":"https://pith.science/paper/TONNF7SQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00269&json=true","fetch_graph":"https://pith.science/api/pith-number/TONNF7SQXQB4JE6RGONWKVXHKC/graph.json","fetch_events":"https://pith.science/api/pith-number/TONNF7SQXQB4JE6RGONWKVXHKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC/action/storage_attestation","attest_author":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC/action/author_attestation","sign_citation":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC/action/citation_signature","submit_replication":"https://pith.science/pith/TONNF7SQXQB4JE6RGONWKVXHKC/action/replication_record"}},"created_at":"2026-07-05T07:21:11.813757+00:00","updated_at":"2026-07-05T07:21:11.813757+00:00"}