{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EINMWNX323GOEBQMX5XQAPBXUA","short_pith_number":"pith:EINMWNX3","schema_version":"1.0","canonical_sha256":"221acb36fbd6cce2060cbf6f003c37a00fd586778501ac6de2bfc8a6c6a1c9c3","source":{"kind":"arxiv","id":"2501.07771","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of Serverless Cloud Infrastructure for Large-Scale Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Ritter, David Justen, Theo Radig, Thomas Bodner, Tilmann Rabl","submitted_at":"2025-01-14T01:07:21Z","abstract_excerpt":"Data processing systems are increasingly deployed in the cloud. While monolithic systems run fully on virtual servers, recent systems embrace cloud infrastructure and utilize the disaggregation of compute and storage to scale them independently. The introduction of serverless compute services, such as AWS Lambda, enables finer-grained and elastic scalability within these systems. Prior work shows the viability of serverless infrastructure for scalable data processing yet also sees limitations due to variable performance and cost overhead, in particular for networking and storage.\n  In this pap"},"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":"2501.07771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-14T01:07:21Z","cross_cats_sorted":[],"title_canon_sha256":"310eac6609528d2ab233abebe60f89e3e5eff5f92199ba665b10ea0fc07294f7","abstract_canon_sha256":"9c49f871ab6500e12552e88e8c9980a3adaf834e9f4ffe67daf33f5b67df93f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:49.847429Z","signature_b64":"WRzidNhlv7IXKIBsp1C4WmOmA93pqTMlbKXoOicp+FNSs38nRW1G9ek23CKJZCjU9DpGWwcbTfB1GjfK0dZzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"221acb36fbd6cce2060cbf6f003c37a00fd586778501ac6de2bfc8a6c6a1c9c3","last_reissued_at":"2026-07-05T10:00:49.846994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:49.846994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of Serverless Cloud Infrastructure for Large-Scale Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Daniel Ritter, David Justen, Theo Radig, Thomas Bodner, Tilmann Rabl","submitted_at":"2025-01-14T01:07:21Z","abstract_excerpt":"Data processing systems are increasingly deployed in the cloud. While monolithic systems run fully on virtual servers, recent systems embrace cloud infrastructure and utilize the disaggregation of compute and storage to scale them independently. The introduction of serverless compute services, such as AWS Lambda, enables finer-grained and elastic scalability within these systems. Prior work shows the viability of serverless infrastructure for scalable data processing yet also sees limitations due to variable performance and cost overhead, in particular for networking and storage.\n  In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07771","kind":"arxiv","version":1},"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/2501.07771/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":"2501.07771","created_at":"2026-07-05T10:00:49.847052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07771v1","created_at":"2026-07-05T10:00:49.847052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07771","created_at":"2026-07-05T10:00:49.847052+00:00"},{"alias_kind":"pith_short_12","alias_value":"EINMWNX323GO","created_at":"2026-07-05T10:00:49.847052+00:00"},{"alias_kind":"pith_short_16","alias_value":"EINMWNX323GOEBQM","created_at":"2026-07-05T10:00:49.847052+00:00"},{"alias_kind":"pith_short_8","alias_value":"EINMWNX3","created_at":"2026-07-05T10:00:49.847052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08479","citing_title":"Skyrise: Exploiting Serverless Cloud Infrastructure for Elastic Data Processing","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA","json":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA.json","graph_json":"https://pith.science/api/pith-number/EINMWNX323GOEBQMX5XQAPBXUA/graph.json","events_json":"https://pith.science/api/pith-number/EINMWNX323GOEBQMX5XQAPBXUA/events.json","paper":"https://pith.science/paper/EINMWNX3"},"agent_actions":{"view_html":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA","download_json":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA.json","view_paper":"https://pith.science/paper/EINMWNX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07771&json=true","fetch_graph":"https://pith.science/api/pith-number/EINMWNX323GOEBQMX5XQAPBXUA/graph.json","fetch_events":"https://pith.science/api/pith-number/EINMWNX323GOEBQMX5XQAPBXUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA/action/storage_attestation","attest_author":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA/action/author_attestation","sign_citation":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA/action/citation_signature","submit_replication":"https://pith.science/pith/EINMWNX323GOEBQMX5XQAPBXUA/action/replication_record"}},"created_at":"2026-07-05T10:00:49.847052+00:00","updated_at":"2026-07-05T10:00:49.847052+00:00"}