{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TE7V6A5WEALWYXKWWJMDRLQ4TZ","short_pith_number":"pith:TE7V6A5W","schema_version":"1.0","canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","source":{"kind":"arxiv","id":"2304.05028","version":3},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of Columnar Storage Formats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrew Pavlo, Huanchen Zhang, Jiahong Shen, Wes McKinney, Xinyu Zeng, Yulong Hui","submitted_at":"2023-04-11T07:34:25Z","abstract_excerpt":"Columnar storage is a core component of a modern data analytics system. Although many database management systems (DBMSs) have proprietary storage formats, most provide extensive support to open-source storage formats such as Parquet and ORC to facilitate cross-platform data sharing. But these formats were developed over a decade ago, in the early 2010s, for the Hadoop ecosystem. Since then, both the hardware and workload landscapes have changed.\n  In this paper, we revisit the most widely adopted open-source columnar storage formats (Parquet and ORC) with a deep dive into their internals. We "},"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":"2304.05028","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-11T07:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"3b3eb56992dc8e1283b4fcd3d8b0dcc248476565d7c7e208c02493104a0fa24c","abstract_canon_sha256":"618e549ab92aa2ba34345923b240d0cc6bad33da0c0e31bdf26d6be5270883c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:47.183082Z","signature_b64":"oPuQxne8m9LuSsEH7NkatyH82dVci5oNOkBoIR0OgLryxygvm5wLd4+S4Q8OtQmbB/BHsJ+SkZkzGVVv3ryDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"993f5f03b620176c5d56b25838ae1c9e605b4c97bdeafe208dd1269df820560a","last_reissued_at":"2026-07-05T07:09:47.182570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:47.182570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of Columnar Storage Formats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrew Pavlo, Huanchen Zhang, Jiahong Shen, Wes McKinney, Xinyu Zeng, Yulong Hui","submitted_at":"2023-04-11T07:34:25Z","abstract_excerpt":"Columnar storage is a core component of a modern data analytics system. Although many database management systems (DBMSs) have proprietary storage formats, most provide extensive support to open-source storage formats such as Parquet and ORC to facilitate cross-platform data sharing. But these formats were developed over a decade ago, in the early 2010s, for the Hadoop ecosystem. Since then, both the hardware and workload landscapes have changed.\n  In this paper, we revisit the most widely adopted open-source columnar storage formats (Parquet and ORC) with a deep dive into their internals. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05028","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/2304.05028/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":"2304.05028","created_at":"2026-07-05T07:09:47.182633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05028v3","created_at":"2026-07-05T07:09:47.182633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05028","created_at":"2026-07-05T07:09:47.182633+00:00"},{"alias_kind":"pith_short_12","alias_value":"TE7V6A5WEALW","created_at":"2026-07-05T07:09:47.182633+00:00"},{"alias_kind":"pith_short_16","alias_value":"TE7V6A5WEALWYXKW","created_at":"2026-07-05T07:09:47.182633+00:00"},{"alias_kind":"pith_short_8","alias_value":"TE7V6A5W","created_at":"2026-07-05T07:09:47.182633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14331","citing_title":"Data Formats in Analytical DBMSs: Performance Trade-offs and Future Directions","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ","json":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ.json","graph_json":"https://pith.science/api/pith-number/TE7V6A5WEALWYXKWWJMDRLQ4TZ/graph.json","events_json":"https://pith.science/api/pith-number/TE7V6A5WEALWYXKWWJMDRLQ4TZ/events.json","paper":"https://pith.science/paper/TE7V6A5W"},"agent_actions":{"view_html":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ","download_json":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ.json","view_paper":"https://pith.science/paper/TE7V6A5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05028&json=true","fetch_graph":"https://pith.science/api/pith-number/TE7V6A5WEALWYXKWWJMDRLQ4TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TE7V6A5WEALWYXKWWJMDRLQ4TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/action/storage_attestation","attest_author":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/action/author_attestation","sign_citation":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/action/citation_signature","submit_replication":"https://pith.science/pith/TE7V6A5WEALWYXKWWJMDRLQ4TZ/action/replication_record"}},"created_at":"2026-07-05T07:09:47.182633+00:00","updated_at":"2026-07-05T07:09:47.182633+00:00"}