{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2ZRRCGVRQERRUTB6RYHHH72ZEG","short_pith_number":"pith:2ZRRCGVR","schema_version":"1.0","canonical_sha256":"d663111ab181231a4c3e8e0e73ff592184db298326a19dc495184eac72b2008e","source":{"kind":"arxiv","id":"2310.08697","version":1},"attestation_state":"computed","paper":{"title":"The Data Lakehouse: Data Warehousing and More","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dipankar Mazumdar, Jason Hughes, JB Onofre","submitted_at":"2023-10-12T20:06:37Z","abstract_excerpt":"Relational Database Management Systems designed for Online Analytical Processing (RDBMS-OLAP) have been foundational to democratizing data and enabling analytical use cases such as business intelligence and reporting for many years. However, RDBMS-OLAP systems present some well-known challenges. They are primarily optimized only for relational workloads, lead to proliferation of data copies which can become unmanageable, and since the data is stored in proprietary formats, it can lead to vendor lock-in, restricting access to engines, tools, and capabilities beyond what the vendor offers. As th"},"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":"2310.08697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-12T20:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"ea05181d5e2eae903052db5e11c2e494432f9bd333a513b458080e3291025459","abstract_canon_sha256":"19b0b40f4e283c8db6566cd634d1182517c110bb1d73864ea4c9bb816148a185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:33.422008Z","signature_b64":"Pfvobimht9QWwqaygrCIq5IqsrsBlKC/tqw6DOKAzYVWgxOccZQALnNVbg6b8Wc4hoLsMeVoFrGx9E/iXsU8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d663111ab181231a4c3e8e0e73ff592184db298326a19dc495184eac72b2008e","last_reissued_at":"2026-07-05T07:00:33.421598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:33.421598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Data Lakehouse: Data Warehousing and More","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dipankar Mazumdar, Jason Hughes, JB Onofre","submitted_at":"2023-10-12T20:06:37Z","abstract_excerpt":"Relational Database Management Systems designed for Online Analytical Processing (RDBMS-OLAP) have been foundational to democratizing data and enabling analytical use cases such as business intelligence and reporting for many years. However, RDBMS-OLAP systems present some well-known challenges. They are primarily optimized only for relational workloads, lead to proliferation of data copies which can become unmanageable, and since the data is stored in proprietary formats, it can lead to vendor lock-in, restricting access to engines, tools, and capabilities beyond what the vendor offers. As th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08697","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/2310.08697/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":"2310.08697","created_at":"2026-07-05T07:00:33.421662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08697v1","created_at":"2026-07-05T07:00:33.421662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08697","created_at":"2026-07-05T07:00:33.421662+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZRRCGVRQERR","created_at":"2026-07-05T07:00:33.421662+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZRRCGVRQERRUTB6","created_at":"2026-07-05T07:00:33.421662+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZRRCGVR","created_at":"2026-07-05T07:00:33.421662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13750","citing_title":"Eudoxia: a FaaS scheduling simulator for the composable lakehouse","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG","json":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG.json","graph_json":"https://pith.science/api/pith-number/2ZRRCGVRQERRUTB6RYHHH72ZEG/graph.json","events_json":"https://pith.science/api/pith-number/2ZRRCGVRQERRUTB6RYHHH72ZEG/events.json","paper":"https://pith.science/paper/2ZRRCGVR"},"agent_actions":{"view_html":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG","download_json":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG.json","view_paper":"https://pith.science/paper/2ZRRCGVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08697&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZRRCGVRQERRUTB6RYHHH72ZEG/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZRRCGVRQERRUTB6RYHHH72ZEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG/action/storage_attestation","attest_author":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG/action/author_attestation","sign_citation":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG/action/citation_signature","submit_replication":"https://pith.science/pith/2ZRRCGVRQERRUTB6RYHHH72ZEG/action/replication_record"}},"created_at":"2026-07-05T07:00:33.421662+00:00","updated_at":"2026-07-05T07:00:33.421662+00:00"}