{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RK2QVAIKGQDXRXAF7I6LLATD6P","short_pith_number":"pith:RK2QVAIK","schema_version":"1.0","canonical_sha256":"8ab50a810a340778dc05fa3cb58263f3f503d5ab8a94ace7fa7e70ab035c9e6a","source":{"kind":"arxiv","id":"2305.01120","version":3},"attestation_state":"computed","paper":{"title":"LST-Bench: Benchmarking Log-Structured Tables in the Cloud","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anja Gruenheid, Ashit Gosalia, Ashvin Agrawal, Avrilia Floratou, Carlo Curino, Cristian Petculescu, Jes\\'us Camacho-Rodr\\'iguez, Josep Aguilar-Saborit, Raghu Ramakrishnan","submitted_at":"2023-05-01T23:15:17Z","abstract_excerpt":"Data processing engines increasingly leverage distributed file systems for scalable, cost-effective storage. While the Apache Parquet columnar format has become a popular choice for data storage and retrieval, the immutability of Parquet files renders it impractical to meet the demands of frequent updates in contemporary analytical workloads. Log-Structured Tables (LSTs), such as Delta Lake, Apache Iceberg, and Apache Hudi, offer an alternative for scenarios requiring data mutability, providing a balance between efficient updates and the benefits of columnar storage. They provide features like"},"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":"2305.01120","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-01T23:15:17Z","cross_cats_sorted":[],"title_canon_sha256":"f113607637115c8695a5260c192b338286d019e45755a7255c59ff2cb207c5a6","abstract_canon_sha256":"2ddcaf434bbbdee0ecaf7cfdceb183b4c500752f2fc848942fa81a56a10b14a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:18.739944Z","signature_b64":"XAObr/X3l7xdjUk6des/Ap2zwBTH2GAxIlm6/q3jun88/1u3ebY+iFiAE87rNBMfKRzFu/KwHp5r+2XlKzSCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ab50a810a340778dc05fa3cb58263f3f503d5ab8a94ace7fa7e70ab035c9e6a","last_reissued_at":"2026-07-05T07:35:18.739406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:18.739406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LST-Bench: Benchmarking Log-Structured Tables in the Cloud","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anja Gruenheid, Ashit Gosalia, Ashvin Agrawal, Avrilia Floratou, Carlo Curino, Cristian Petculescu, Jes\\'us Camacho-Rodr\\'iguez, Josep Aguilar-Saborit, Raghu Ramakrishnan","submitted_at":"2023-05-01T23:15:17Z","abstract_excerpt":"Data processing engines increasingly leverage distributed file systems for scalable, cost-effective storage. While the Apache Parquet columnar format has become a popular choice for data storage and retrieval, the immutability of Parquet files renders it impractical to meet the demands of frequent updates in contemporary analytical workloads. Log-Structured Tables (LSTs), such as Delta Lake, Apache Iceberg, and Apache Hudi, offer an alternative for scenarios requiring data mutability, providing a balance between efficient updates and the benefits of columnar storage. They provide features like"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01120","kind":"arxiv","version":3},"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/2305.01120/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":"2305.01120","created_at":"2026-07-05T07:35:18.739467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01120v3","created_at":"2026-07-05T07:35:18.739467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01120","created_at":"2026-07-05T07:35:18.739467+00:00"},{"alias_kind":"pith_short_12","alias_value":"RK2QVAIKGQDX","created_at":"2026-07-05T07:35:18.739467+00:00"},{"alias_kind":"pith_short_16","alias_value":"RK2QVAIKGQDXRXAF","created_at":"2026-07-05T07:35:18.739467+00:00"},{"alias_kind":"pith_short_8","alias_value":"RK2QVAIK","created_at":"2026-07-05T07:35:18.739467+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/RK2QVAIKGQDXRXAF7I6LLATD6P","json":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P.json","graph_json":"https://pith.science/api/pith-number/RK2QVAIKGQDXRXAF7I6LLATD6P/graph.json","events_json":"https://pith.science/api/pith-number/RK2QVAIKGQDXRXAF7I6LLATD6P/events.json","paper":"https://pith.science/paper/RK2QVAIK"},"agent_actions":{"view_html":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P","download_json":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P.json","view_paper":"https://pith.science/paper/RK2QVAIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01120&json=true","fetch_graph":"https://pith.science/api/pith-number/RK2QVAIKGQDXRXAF7I6LLATD6P/graph.json","fetch_events":"https://pith.science/api/pith-number/RK2QVAIKGQDXRXAF7I6LLATD6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P/action/storage_attestation","attest_author":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P/action/author_attestation","sign_citation":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P/action/citation_signature","submit_replication":"https://pith.science/pith/RK2QVAIKGQDXRXAF7I6LLATD6P/action/replication_record"}},"created_at":"2026-07-05T07:35:18.739467+00:00","updated_at":"2026-07-05T07:35:18.739467+00:00"}