{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LQ2CFEEMQGRLXHJ4FGXRP66JRB","short_pith_number":"pith:LQ2CFEEM","schema_version":"1.0","canonical_sha256":"5c3422908c81a2bb9d3c29af17fbc9885a0f9e3126c9d7e22603bdf4f34406d8","source":{"kind":"arxiv","id":"2106.09592","version":2},"attestation_state":"computed","paper":{"title":"Data Lakes: A Survey of Functions and Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christoph Quix, Christos Koutras, Matthias Jarke, Rihan Hai","submitted_at":"2021-06-17T15:18:23Z","abstract_excerpt":"Data lakes are becoming increasingly prevalent for big data management and data analytics. In contrast to traditional 'schema-on-write' approaches such as data warehouses, data lakes are repositories storing raw data in its original formats and providing a common access interface. Despite the strong interest raised from both academia and industry, there is a large body of ambiguity regarding the definition, functions and available technologies for data lakes. A complete, coherent picture of data lake challenges and solutions is still missing. This survey reviews the development, architectures,"},"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":"2106.09592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-17T15:18:23Z","cross_cats_sorted":[],"title_canon_sha256":"091226f6a218b18ea2b30debf58e83dbd81eab6385156a8a5f2e9d7b4ef80833","abstract_canon_sha256":"1b5aba5c7bb4ce3a4bfa21ec22297023bc95f6e937a05d6b8fc3bdce722b832c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:16.475688Z","signature_b64":"WxNkit7IqmDkGXrZKCziC2Ez5YQdKCiwdrZhQ4QPqbOw7WvMSbUDXaIl5RfOvdeIdFiHrg/DuR3C5WrxuJ1hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3422908c81a2bb9d3c29af17fbc9885a0f9e3126c9d7e22603bdf4f34406d8","last_reissued_at":"2026-07-05T07:03:16.475295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:16.475295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Lakes: A Survey of Functions and Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christoph Quix, Christos Koutras, Matthias Jarke, Rihan Hai","submitted_at":"2021-06-17T15:18:23Z","abstract_excerpt":"Data lakes are becoming increasingly prevalent for big data management and data analytics. In contrast to traditional 'schema-on-write' approaches such as data warehouses, data lakes are repositories storing raw data in its original formats and providing a common access interface. Despite the strong interest raised from both academia and industry, there is a large body of ambiguity regarding the definition, functions and available technologies for data lakes. A complete, coherent picture of data lake challenges and solutions is still missing. This survey reviews the development, architectures,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09592","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/2106.09592/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":"2106.09592","created_at":"2026-07-05T07:03:16.475353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09592v2","created_at":"2026-07-05T07:03:16.475353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09592","created_at":"2026-07-05T07:03:16.475353+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ2CFEEMQGRL","created_at":"2026-07-05T07:03:16.475353+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ2CFEEMQGRLXHJ4","created_at":"2026-07-05T07:03:16.475353+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ2CFEEM","created_at":"2026-07-05T07:03:16.475353+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/LQ2CFEEMQGRLXHJ4FGXRP66JRB","json":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB.json","graph_json":"https://pith.science/api/pith-number/LQ2CFEEMQGRLXHJ4FGXRP66JRB/graph.json","events_json":"https://pith.science/api/pith-number/LQ2CFEEMQGRLXHJ4FGXRP66JRB/events.json","paper":"https://pith.science/paper/LQ2CFEEM"},"agent_actions":{"view_html":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB","download_json":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB.json","view_paper":"https://pith.science/paper/LQ2CFEEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09592&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ2CFEEMQGRLXHJ4FGXRP66JRB/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ2CFEEMQGRLXHJ4FGXRP66JRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB/action/storage_attestation","attest_author":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB/action/author_attestation","sign_citation":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB/action/citation_signature","submit_replication":"https://pith.science/pith/LQ2CFEEMQGRLXHJ4FGXRP66JRB/action/replication_record"}},"created_at":"2026-07-05T07:03:16.475353+00:00","updated_at":"2026-07-05T07:03:16.475353+00:00"}