{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FEHANRVZ3UIHPPVUFQY7RNPTZZ","short_pith_number":"pith:FEHANRVZ","schema_version":"1.0","canonical_sha256":"290e06c6b9dd1077beb42c31f8b5f3ce4a50c94af7c5dc267853c3504063b449","source":{"kind":"arxiv","id":"1803.06354","version":2},"attestation_state":"computed","paper":{"title":"Serverless Data Analytics with Flint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.DC","authors_text":"Jimmy Lin, YoungBin Kim","submitted_at":"2018-03-16T18:02:27Z","abstract_excerpt":"Serverless architectures organized around loosely-coupled function invocations represent an emerging design for many applications. Recent work mostly focuses on user-facing products and event-driven processing pipelines. In this paper, we explore a completely different part of the application space and examine the feasibility of analytical processing on big data using a serverless architecture. We present Flint, a prototype Spark execution engine that takes advantage of AWS Lambda to provide a pure pay-as-you-go cost model. With Flint, a developer uses PySpark exactly as before, but without ne"},"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":"1803.06354","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-03-16T18:02:27Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"e20656489c9d589e93b8fa510788df75f0900ae893a22ddb132d55d5fab416bc","abstract_canon_sha256":"dbadfa1194fc060bc4337dcfe594b58f3923d3df5b5daaa0d286f805add2f03d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:41.463431Z","signature_b64":"DR02o0O9SMjMUJDQ0pITv09Jxaw4qkQZ4Aee0DwLJ2+wsxB76WKuO5gpB9MAsuZ4awYuWT81khYtTF2UwcMdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290e06c6b9dd1077beb42c31f8b5f3ce4a50c94af7c5dc267853c3504063b449","last_reissued_at":"2026-05-18T00:03:41.462855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:41.462855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Serverless Data Analytics with Flint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.DC","authors_text":"Jimmy Lin, YoungBin Kim","submitted_at":"2018-03-16T18:02:27Z","abstract_excerpt":"Serverless architectures organized around loosely-coupled function invocations represent an emerging design for many applications. Recent work mostly focuses on user-facing products and event-driven processing pipelines. In this paper, we explore a completely different part of the application space and examine the feasibility of analytical processing on big data using a serverless architecture. We present Flint, a prototype Spark execution engine that takes advantage of AWS Lambda to provide a pure pay-as-you-go cost model. With Flint, a developer uses PySpark exactly as before, but without ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06354","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":""},"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":"1803.06354","created_at":"2026-05-18T00:03:41.462919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06354v2","created_at":"2026-05-18T00:03:41.462919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06354","created_at":"2026-05-18T00:03:41.462919+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEHANRVZ3UIH","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEHANRVZ3UIHPPVU","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEHANRVZ","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11465","citing_title":"ServerMix: Tradeoffs and Challenges of Serverless Data Analytics","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ","json":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ.json","graph_json":"https://pith.science/api/pith-number/FEHANRVZ3UIHPPVUFQY7RNPTZZ/graph.json","events_json":"https://pith.science/api/pith-number/FEHANRVZ3UIHPPVUFQY7RNPTZZ/events.json","paper":"https://pith.science/paper/FEHANRVZ"},"agent_actions":{"view_html":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ","download_json":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ.json","view_paper":"https://pith.science/paper/FEHANRVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06354&json=true","fetch_graph":"https://pith.science/api/pith-number/FEHANRVZ3UIHPPVUFQY7RNPTZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FEHANRVZ3UIHPPVUFQY7RNPTZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ/action/storage_attestation","attest_author":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ/action/author_attestation","sign_citation":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ/action/citation_signature","submit_replication":"https://pith.science/pith/FEHANRVZ3UIHPPVUFQY7RNPTZZ/action/replication_record"}},"created_at":"2026-05-18T00:03:41.462919+00:00","updated_at":"2026-05-18T00:03:41.462919+00:00"}