{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KOJGECIVS3IDLGYEYN6B3BLDBJ","short_pith_number":"pith:KOJGECIV","schema_version":"1.0","canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","source":{"kind":"arxiv","id":"1804.00224","version":1},"attestation_state":"computed","paper":{"title":"A comparative analysis of state-of-the-art SQL-on-Hadoop systems for interactive analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ashish Tapdiya, Daniel Fabbri","submitted_at":"2018-03-31T23:16:01Z","abstract_excerpt":"Hadoop is emerging as the primary data hub in enterprises, and SQL represents the de facto language for data analysis. This combination has led to the development of a variety of SQL-on-Hadoop systems in use today. While the various SQL-on-Hadoop systems target the same class of analytical workloads, their different architectures, design decisions and implementations impact query performance. In this work, we perform a comparative analysis of four state-of-the-art SQL-on-Hadoop systems (Impala, Drill, Spark SQL and Phoenix) using the Web Data Analytics micro benchmark and the TPC-H benchmark o"},"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":"1804.00224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-31T23:16:01Z","cross_cats_sorted":[],"title_canon_sha256":"6f52339741f101b82d66299642cbe7c5a51c0898f9fa19f576c93ee073785938","abstract_canon_sha256":"683f0fb652cac7cb921579f881ceac61672c54de2c6786412a7c6397d32f9347"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:37.983073Z","signature_b64":"8J3VTK4OOUa4z9coePAxiARAYii4X7TC1c/AmPD7IVtRnj0bMqXXyOZbmjL66SaMnwjWSlVWnXGQGbevvrm9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","last_reissued_at":"2026-05-18T00:19:37.982286Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:37.982286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparative analysis of state-of-the-art SQL-on-Hadoop systems for interactive analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ashish Tapdiya, Daniel Fabbri","submitted_at":"2018-03-31T23:16:01Z","abstract_excerpt":"Hadoop is emerging as the primary data hub in enterprises, and SQL represents the de facto language for data analysis. This combination has led to the development of a variety of SQL-on-Hadoop systems in use today. While the various SQL-on-Hadoop systems target the same class of analytical workloads, their different architectures, design decisions and implementations impact query performance. In this work, we perform a comparative analysis of four state-of-the-art SQL-on-Hadoop systems (Impala, Drill, Spark SQL and Phoenix) using the Web Data Analytics micro benchmark and the TPC-H benchmark o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00224","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":""},"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":"1804.00224","created_at":"2026-05-18T00:19:37.982426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00224v1","created_at":"2026-05-18T00:19:37.982426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00224","created_at":"2026-05-18T00:19:37.982426+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOJGECIVS3ID","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOJGECIVS3IDLGYE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOJGECIV","created_at":"2026-05-18T12:32:33.847187+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/KOJGECIVS3IDLGYEYN6B3BLDBJ","json":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ.json","graph_json":"https://pith.science/api/pith-number/KOJGECIVS3IDLGYEYN6B3BLDBJ/graph.json","events_json":"https://pith.science/api/pith-number/KOJGECIVS3IDLGYEYN6B3BLDBJ/events.json","paper":"https://pith.science/paper/KOJGECIV"},"agent_actions":{"view_html":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ","download_json":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ.json","view_paper":"https://pith.science/paper/KOJGECIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00224&json=true","fetch_graph":"https://pith.science/api/pith-number/KOJGECIVS3IDLGYEYN6B3BLDBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KOJGECIVS3IDLGYEYN6B3BLDBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/action/storage_attestation","attest_author":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/action/author_attestation","sign_citation":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/action/citation_signature","submit_replication":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/action/replication_record"}},"created_at":"2026-05-18T00:19:37.982426+00:00","updated_at":"2026-05-18T00:19:37.982426+00:00"}