{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YETU2XTXXBQEILDRD36MUFB74K","short_pith_number":"pith:YETU2XTX","schema_version":"1.0","canonical_sha256":"c1274d5e77b860442c711efcca143fe2b61bfb4d7f9ede339bcb450e22ad8c28","source":{"kind":"arxiv","id":"1709.10072","version":1},"attestation_state":"computed","paper":{"title":"A Simple and Efficient MapReduce Algorithm for Data Cube Materialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Mukund Sundararajan, Qiqi Yan","submitted_at":"2017-09-28T17:26:32Z","abstract_excerpt":"Data cube materialization is a classical database operator introduced in Gray et al.~(Data Mining and Knowledge Discovery, Vol.~1), which is critical for many analysis tasks. Nandi et al.~(Transactions on Knowledge and Data Engineering, Vol.~6) first studied cube materialization for large scale datasets using the MapReduce framework, and proposed a sophisticated modification of a simple broadcast algorithm to handle a dataset with a 216GB cube size within 25 minutes with 2k machines in 2012. We take a different approach, and propose a simple MapReduce algorithm which (1) minimizes the total nu"},"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":"1709.10072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-28T17:26:32Z","cross_cats_sorted":[],"title_canon_sha256":"43fbd96ff9d03a6eb357a127acbd8a47fad7597adee1459a9d4f0b35c3c964d8","abstract_canon_sha256":"2a6d42b5676b724584947a53102e3770b75d1445c9b080e217380475acde102a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:05.760661Z","signature_b64":"z6VKwm/eETHLKLHN9h6xKZEvZLG2lqZGEY5ccUoyLkr05wKuhUlmQ8UUDVoD0mMk4x5Lp/Ri0htbb2RTh09wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1274d5e77b860442c711efcca143fe2b61bfb4d7f9ede339bcb450e22ad8c28","last_reissued_at":"2026-05-18T00:34:05.759951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:05.759951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple and Efficient MapReduce Algorithm for Data Cube Materialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Mukund Sundararajan, Qiqi Yan","submitted_at":"2017-09-28T17:26:32Z","abstract_excerpt":"Data cube materialization is a classical database operator introduced in Gray et al.~(Data Mining and Knowledge Discovery, Vol.~1), which is critical for many analysis tasks. Nandi et al.~(Transactions on Knowledge and Data Engineering, Vol.~6) first studied cube materialization for large scale datasets using the MapReduce framework, and proposed a sophisticated modification of a simple broadcast algorithm to handle a dataset with a 216GB cube size within 25 minutes with 2k machines in 2012. We take a different approach, and propose a simple MapReduce algorithm which (1) minimizes the total nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10072","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":"1709.10072","created_at":"2026-05-18T00:34:05.760071+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.10072v1","created_at":"2026-05-18T00:34:05.760071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10072","created_at":"2026-05-18T00:34:05.760071+00:00"},{"alias_kind":"pith_short_12","alias_value":"YETU2XTXXBQE","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YETU2XTXXBQEILDR","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YETU2XTX","created_at":"2026-05-18T12:31:56.362134+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/YETU2XTXXBQEILDRD36MUFB74K","json":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K.json","graph_json":"https://pith.science/api/pith-number/YETU2XTXXBQEILDRD36MUFB74K/graph.json","events_json":"https://pith.science/api/pith-number/YETU2XTXXBQEILDRD36MUFB74K/events.json","paper":"https://pith.science/paper/YETU2XTX"},"agent_actions":{"view_html":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K","download_json":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K.json","view_paper":"https://pith.science/paper/YETU2XTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.10072&json=true","fetch_graph":"https://pith.science/api/pith-number/YETU2XTXXBQEILDRD36MUFB74K/graph.json","fetch_events":"https://pith.science/api/pith-number/YETU2XTXXBQEILDRD36MUFB74K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K/action/storage_attestation","attest_author":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K/action/author_attestation","sign_citation":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K/action/citation_signature","submit_replication":"https://pith.science/pith/YETU2XTXXBQEILDRD36MUFB74K/action/replication_record"}},"created_at":"2026-05-18T00:34:05.760071+00:00","updated_at":"2026-05-18T00:34:05.760071+00:00"}