{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XUL3UW3ZGUPXD3ROFD6VF7NUMN","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":"b2fe15f1073cb4e88d374d8598b10b25274cd21242a79c5b020f1b8370aaf73f","cross_cats_sorted":["cs.DB","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T12:26:38Z","title_canon_sha256":"b9450dd6d8acd54af64e3a0cea9768bd656cac4db9337e6f04426a7a44dccc06"},"schema_version":"1.0","source":{"id":"1907.01882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01882","created_at":"2026-07-04T23:51:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01882v2","created_at":"2026-07-04T23:51:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01882","created_at":"2026-07-04T23:51:23Z"},{"alias_kind":"pith_short_12","alias_value":"XUL3UW3ZGUPX","created_at":"2026-07-04T23:51:23Z"},{"alias_kind":"pith_short_16","alias_value":"XUL3UW3ZGUPXD3RO","created_at":"2026-07-04T23:51:23Z"},{"alias_kind":"pith_short_8","alias_value":"XUL3UW3Z","created_at":"2026-07-04T23:51:23Z"}],"graph_snapshots":[{"event_id":"sha256:aa8c2ea0077e6931b951798cdd8c018de7ea2849f02dc383e90eeaa722773ff4","target":"graph","created_at":"2026-07-04T23:51:23Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.01882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient boosting decision tree (GBDT) is a widely-used machine learning algorithm in both data analytic competitions and real-world industrial applications. Further, driven by the rapid increase in data volume, efforts have been made to train GBDT in a distributed setting to support large-scale workloads. However, we find it surprising that the existing systems manage the training dataset in different ways, but none of them have studied the impact of data management. To that end, this paper aims to study the pros and cons of different data management methods regarding the performance of distr","authors_text":"Bin Cui, Fangcheng Fu, Jiawei Jiang, Yingxia Shao","cross_cats":["cs.DB","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T12:26:38Z","title":"An Experimental Evaluation of Large Scale GBDT Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01882","kind":"arxiv","version":2},"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:bb5ab12155d3c8de76ef7e24a8e96e27afd9328b749b670567ac193eb24cde1e","target":"record","created_at":"2026-07-04T23:51:23Z","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":"b2fe15f1073cb4e88d374d8598b10b25274cd21242a79c5b020f1b8370aaf73f","cross_cats_sorted":["cs.DB","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T12:26:38Z","title_canon_sha256":"b9450dd6d8acd54af64e3a0cea9768bd656cac4db9337e6f04426a7a44dccc06"},"schema_version":"1.0","source":{"id":"1907.01882","kind":"arxiv","version":2}},"canonical_sha256":"bd17ba5b79351f71ee2e28fd52fdb463674dd675818caf3d60365d3b26c11035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd17ba5b79351f71ee2e28fd52fdb463674dd675818caf3d60365d3b26c11035","first_computed_at":"2026-07-04T23:51:23.773517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:23.773517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"soL4efSJm4IjUQxFndFYd6QK3qQED2SQWaQcEC2P4yuh12AOnxc6t1mtrzbdIf9y7p67+YJR+/gFxWS9WDF/Bw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:23.773913Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.01882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb5ab12155d3c8de76ef7e24a8e96e27afd9328b749b670567ac193eb24cde1e","sha256:aa8c2ea0077e6931b951798cdd8c018de7ea2849f02dc383e90eeaa722773ff4"],"state_sha256":"dbeb9711c2abbcf75b8c1648f3adee66353ed85569a5e21fa240b16c2c32a0d8"}