{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XUL3UW3ZGUPXD3ROFD6VF7NUMN","short_pith_number":"pith:XUL3UW3Z","canonical_record":{"source":{"id":"1907.01882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T12:26:38Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"b9450dd6d8acd54af64e3a0cea9768bd656cac4db9337e6f04426a7a44dccc06","abstract_canon_sha256":"b2fe15f1073cb4e88d374d8598b10b25274cd21242a79c5b020f1b8370aaf73f"},"schema_version":"1.0"},"canonical_sha256":"bd17ba5b79351f71ee2e28fd52fdb463674dd675818caf3d60365d3b26c11035","source":{"kind":"arxiv","id":"1907.01882","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XUL3UW3ZGUPXD3ROFD6VF7NUMN","target":"record","payload":{"canonical_record":{"source":{"id":"1907.01882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T12:26:38Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"b9450dd6d8acd54af64e3a0cea9768bd656cac4db9337e6f04426a7a44dccc06","abstract_canon_sha256":"b2fe15f1073cb4e88d374d8598b10b25274cd21242a79c5b020f1b8370aaf73f"},"schema_version":"1.0"},"canonical_sha256":"bd17ba5b79351f71ee2e28fd52fdb463674dd675818caf3d60365d3b26c11035","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:23.773913Z","signature_b64":"soL4efSJm4IjUQxFndFYd6QK3qQED2SQWaQcEC2P4yuh12AOnxc6t1mtrzbdIf9y7p67+YJR+/gFxWS9WDF/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd17ba5b79351f71ee2e28fd52fdb463674dd675818caf3d60365d3b26c11035","last_reissued_at":"2026-07-04T23:51:23.773517Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:23.773517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.01882","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:51:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVlin6loarw+QB+b1x7iZWehC+XIDdLA+U8as+6NmYqg5gTCCYqQC+R7nSZT/q/jVVps1SxaOa7R+ErLBWGyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:17:33.896561Z"},"content_sha256":"bb5ab12155d3c8de76ef7e24a8e96e27afd9328b749b670567ac193eb24cde1e","schema_version":"1.0","event_id":"sha256:bb5ab12155d3c8de76ef7e24a8e96e27afd9328b749b670567ac193eb24cde1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XUL3UW3ZGUPXD3ROFD6VF7NUMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Experimental Evaluation of Large Scale GBDT Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Fangcheng Fu, Jiawei Jiang, Yingxia Shao","submitted_at":"2019-07-03T12:26:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01882","kind":"arxiv","version":2},"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/1907.01882/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:51:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"161f2C2Poi7ZXip0EjTUV8ASOeJ46N/Oxxah3yDt8vZJwdH7G4PWIPqQ6ggbkLXCKEESbOticVvaF5CGGPmNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:17:33.897188Z"},"content_sha256":"aa8c2ea0077e6931b951798cdd8c018de7ea2849f02dc383e90eeaa722773ff4","schema_version":"1.0","event_id":"sha256:aa8c2ea0077e6931b951798cdd8c018de7ea2849f02dc383e90eeaa722773ff4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/bundle.json","state_url":"https://pith.science/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/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":"2026-08-18T18:17:33Z","links":{"resolver":"https://pith.science/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN","bundle":"https://pith.science/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/bundle.json","state":"https://pith.science/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUL3UW3ZGUPXD3ROFD6VF7NUMN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fINninKzesUrtrZfmvqEKujGoIFnPoP4sG3ri2Td7A2YGXWgXf21a/2jl727hQZs+pxguAKRtLs8b2RBjpNaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:17:33.901054Z","bundle_sha256":"53036030357a0490eca255a66c7f74162f4dc21968a293c78883d62b90ffc023"}}