{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MQMEJBOB7H4LMMK4NHTL4VJ4RI","short_pith_number":"pith:MQMEJBOB","schema_version":"1.0","canonical_sha256":"64184485c1f9f8b6315c69e6be553c8a0dc4c22753c7ed4a6033064725519829","source":{"kind":"arxiv","id":"1810.07748","version":1},"attestation_state":"computed","paper":{"title":"A Parallel Random Forest Algorithm for Big Data in a Spark Cloud Computing Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chuliang Weng, Jianguo Chen, Kashif Bilal, Kenli Li, Keqin Li, Shui Yu, Zhuo Tang","submitted_at":"2018-10-17T19:40:14Z","abstract_excerpt":"With the emergence of the big data age, the issue of how to obtain valuable knowledge from a dataset efficiently and accurately has attracted increasingly attention from both academia and industry. This paper presents a Parallel Random Forest (PRF) algorithm for big data on the Apache Spark platform. The PRF algorithm is optimized based on a hybrid approach combining data-parallel and task-parallel optimization. From the perspective of data-parallel optimization, a vertical data-partitioning method is performed to reduce the data communication cost effectively, and a data-multiplexing method i"},"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":"1810.07748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-10-17T19:40:14Z","cross_cats_sorted":[],"title_canon_sha256":"916e9b4ab153ed44bb9c9cf5270a2a7820c2d67f2bf4436484f5a61ecf5e6117","abstract_canon_sha256":"ae2dc96a0d087524f408258331ba3df60031785d05c6fc43015d26b5127fd07a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:22.319056Z","signature_b64":"++w/uWtwshwEGPV5m6ZI6WZ+ZgEZUxBt9QhkcOaSrun5D++TbWQPiwxtsoy+FAkmOf39tRQK9/WhHp36V0vQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64184485c1f9f8b6315c69e6be553c8a0dc4c22753c7ed4a6033064725519829","last_reissued_at":"2026-07-05T00:21:22.318581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:22.318581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Parallel Random Forest Algorithm for Big Data in a Spark Cloud Computing Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chuliang Weng, Jianguo Chen, Kashif Bilal, Kenli Li, Keqin Li, Shui Yu, Zhuo Tang","submitted_at":"2018-10-17T19:40:14Z","abstract_excerpt":"With the emergence of the big data age, the issue of how to obtain valuable knowledge from a dataset efficiently and accurately has attracted increasingly attention from both academia and industry. This paper presents a Parallel Random Forest (PRF) algorithm for big data on the Apache Spark platform. The PRF algorithm is optimized based on a hybrid approach combining data-parallel and task-parallel optimization. From the perspective of data-parallel optimization, a vertical data-partitioning method is performed to reduce the data communication cost effectively, and a data-multiplexing method i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07748","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.07748/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":"1810.07748","created_at":"2026-07-05T00:21:22.318658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07748v1","created_at":"2026-07-05T00:21:22.318658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07748","created_at":"2026-07-05T00:21:22.318658+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQMEJBOB7H4L","created_at":"2026-07-05T00:21:22.318658+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQMEJBOB7H4LMMK4","created_at":"2026-07-05T00:21:22.318658+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQMEJBOB","created_at":"2026-07-05T00:21:22.318658+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/MQMEJBOB7H4LMMK4NHTL4VJ4RI","json":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI.json","graph_json":"https://pith.science/api/pith-number/MQMEJBOB7H4LMMK4NHTL4VJ4RI/graph.json","events_json":"https://pith.science/api/pith-number/MQMEJBOB7H4LMMK4NHTL4VJ4RI/events.json","paper":"https://pith.science/paper/MQMEJBOB"},"agent_actions":{"view_html":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI","download_json":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI.json","view_paper":"https://pith.science/paper/MQMEJBOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07748&json=true","fetch_graph":"https://pith.science/api/pith-number/MQMEJBOB7H4LMMK4NHTL4VJ4RI/graph.json","fetch_events":"https://pith.science/api/pith-number/MQMEJBOB7H4LMMK4NHTL4VJ4RI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI/action/storage_attestation","attest_author":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI/action/author_attestation","sign_citation":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI/action/citation_signature","submit_replication":"https://pith.science/pith/MQMEJBOB7H4LMMK4NHTL4VJ4RI/action/replication_record"}},"created_at":"2026-07-05T00:21:22.318658+00:00","updated_at":"2026-07-05T00:21:22.318658+00:00"}