{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LTOSSLM35URTEGU7KAR2K5NBWU","short_pith_number":"pith:LTOSSLM3","schema_version":"1.0","canonical_sha256":"5cdd292d9bed23321a9f5023a575a1b5357d35da6a4260fc3d85e80e79b73d87","source":{"kind":"arxiv","id":"1506.01494","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Big Data Systems: State-of-the-Art and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.PF","authors_text":"Lei Wang, Rui Han, Wanling Gao, Xinhui Tian, Zhen Jia","submitted_at":"2015-06-04T07:48:37Z","abstract_excerpt":"The great prosperity of big data systems such as Hadoop in recent years makes the benchmarking of these systems become crucial for both research and industry communities. The complexity, diversity, and rapid evolution of big data systems gives rise to various new challenges about how we design generators to produce data with the 4V properties (i.e. volume, velocity, variety and veracity), as well as implement application-specific but still comprehensive workloads. However, most of the existing big data benchmarks can be described as attempts to solve specific problems in benchmarking systems. "},"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":"1506.01494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2015-06-04T07:48:37Z","cross_cats_sorted":[],"title_canon_sha256":"5c223f395f1674bf332cae92a8c01b9e90e29a41323fa308a9108ce5036969ab","abstract_canon_sha256":"c4dc5f573eaf70b1b40e70779351f778ccd89175213c16d1c31437f274415231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:57:41.287797Z","signature_b64":"HpvkXq+FQ/TJ5sMnLeAiq8m/mndMdvMWFpx6RhQw7FU127Zp37uqO9PrW2H7py6fa+CEiGAA7Bgj2iguoex1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cdd292d9bed23321a9f5023a575a1b5357d35da6a4260fc3d85e80e79b73d87","last_reissued_at":"2026-05-18T01:57:41.287067Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:57:41.287067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Big Data Systems: State-of-the-Art and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.PF","authors_text":"Lei Wang, Rui Han, Wanling Gao, Xinhui Tian, Zhen Jia","submitted_at":"2015-06-04T07:48:37Z","abstract_excerpt":"The great prosperity of big data systems such as Hadoop in recent years makes the benchmarking of these systems become crucial for both research and industry communities. The complexity, diversity, and rapid evolution of big data systems gives rise to various new challenges about how we design generators to produce data with the 4V properties (i.e. volume, velocity, variety and veracity), as well as implement application-specific but still comprehensive workloads. However, most of the existing big data benchmarks can be described as attempts to solve specific problems in benchmarking systems. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01494","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":"1506.01494","created_at":"2026-05-18T01:57:41.287190+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.01494v1","created_at":"2026-05-18T01:57:41.287190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01494","created_at":"2026-05-18T01:57:41.287190+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTOSSLM35URT","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTOSSLM35URTEGU7","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTOSSLM3","created_at":"2026-05-18T12:29:29.992203+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/LTOSSLM35URTEGU7KAR2K5NBWU","json":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU.json","graph_json":"https://pith.science/api/pith-number/LTOSSLM35URTEGU7KAR2K5NBWU/graph.json","events_json":"https://pith.science/api/pith-number/LTOSSLM35URTEGU7KAR2K5NBWU/events.json","paper":"https://pith.science/paper/LTOSSLM3"},"agent_actions":{"view_html":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU","download_json":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU.json","view_paper":"https://pith.science/paper/LTOSSLM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.01494&json=true","fetch_graph":"https://pith.science/api/pith-number/LTOSSLM35URTEGU7KAR2K5NBWU/graph.json","fetch_events":"https://pith.science/api/pith-number/LTOSSLM35URTEGU7KAR2K5NBWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU/action/storage_attestation","attest_author":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU/action/author_attestation","sign_citation":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU/action/citation_signature","submit_replication":"https://pith.science/pith/LTOSSLM35URTEGU7KAR2K5NBWU/action/replication_record"}},"created_at":"2026-05-18T01:57:41.287190+00:00","updated_at":"2026-05-18T01:57:41.287190+00:00"}