{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KOJGECIVS3IDLGYEYN6B3BLDBJ","short_pith_number":"pith:KOJGECIV","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"},"canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","source":{"kind":"arxiv","id":"1804.00224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00224","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00224v1","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00224","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"KOJGECIVS3ID","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KOJGECIVS3IDLGYE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KOJGECIV","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KOJGECIVS3IDLGYEYN6B3BLDBJ","target":"record","payload":{"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"},"canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","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"},"source_kind":"arxiv","source_id":"1804.00224","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAQX6U8Dyv1tLH5691OQQX/dIQqHC+Z1gQAJ3i8JUy9iVKehi2G7qP3odahd7LINJemdW/4v21OUb5Jy0fq9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:45:57.525971Z"},"content_sha256":"28ea8dddaf17459fe43cda9cc49c8457caa23bc906c2a1d35dff467b9207e7a4","schema_version":"1.0","event_id":"sha256:28ea8dddaf17459fe43cda9cc49c8457caa23bc906c2a1d35dff467b9207e7a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KOJGECIVS3IDLGYEYN6B3BLDBJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWTalbuziVgUZoAwWyfeCaYCnTPa5NcSc/CqGa+1VECVZopDurr8aaUia1LHiN/0tS+bRebenGHCJiuIJSJXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:45:57.526645Z"},"content_sha256":"08bead20fe795b3818dbd98da753c0d13ff374a078c2a61e954eb407f6b29057","schema_version":"1.0","event_id":"sha256:08bead20fe795b3818dbd98da753c0d13ff374a078c2a61e954eb407f6b29057"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/bundle.json","state_url":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T14:45:57Z","links":{"resolver":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ","bundle":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/bundle.json","state":"https://pith.science/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOJGECIVS3IDLGYEYN6B3BLDBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KOJGECIVS3IDLGYEYN6B3BLDBJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"683f0fb652cac7cb921579f881ceac61672c54de2c6786412a7c6397d32f9347","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-31T23:16:01Z","title_canon_sha256":"6f52339741f101b82d66299642cbe7c5a51c0898f9fa19f576c93ee073785938"},"schema_version":"1.0","source":{"id":"1804.00224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00224","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00224v1","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00224","created_at":"2026-05-18T00:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"KOJGECIVS3ID","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KOJGECIVS3IDLGYE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KOJGECIV","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:08bead20fe795b3818dbd98da753c0d13ff374a078c2a61e954eb407f6b29057","target":"graph","created_at":"2026-05-18T00:19:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ashish Tapdiya, Daniel Fabbri","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-31T23:16:01Z","title":"A comparative analysis of state-of-the-art SQL-on-Hadoop systems for interactive analytics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00224","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:28ea8dddaf17459fe43cda9cc49c8457caa23bc906c2a1d35dff467b9207e7a4","target":"record","created_at":"2026-05-18T00:19:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"683f0fb652cac7cb921579f881ceac61672c54de2c6786412a7c6397d32f9347","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-31T23:16:01Z","title_canon_sha256":"6f52339741f101b82d66299642cbe7c5a51c0898f9fa19f576c93ee073785938"},"schema_version":"1.0","source":{"id":"1804.00224","kind":"arxiv","version":1}},"canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"539262091596d0359b04c37c1d85630a448536368f4c1e8edece449db588a36b","first_computed_at":"2026-05-18T00:19:37.982286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:37.982286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8J3VTK4OOUa4z9coePAxiARAYii4X7TC1c/AmPD7IVtRnj0bMqXXyOZbmjL66SaMnwjWSlVWnXGQGbevvrm9DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:37.983073Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.00224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28ea8dddaf17459fe43cda9cc49c8457caa23bc906c2a1d35dff467b9207e7a4","sha256:08bead20fe795b3818dbd98da753c0d13ff374a078c2a61e954eb407f6b29057"],"state_sha256":"5badf47d5ad891d9239a00545fd2caba7e248c44650b3980d168fd466ee2efdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uouVHwj5C/PUzuaQRTjO3SukHbAS4TM8Cat2XKeMpw5cLjuQTPrqTk9EGkQ6qLzD/LKhunE8FXJHV3acjGTKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:45:57.531237Z","bundle_sha256":"17c4616b7dc17f44dc883ad759f560cfa7bb0ecf0bf3fdf87311bb5e252bc11e"}}