{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:22NKOIIAPLXHCYYR2VC2KVJT2Z","short_pith_number":"pith:22NKOIIA","schema_version":"1.0","canonical_sha256":"d69aa721007aee716311d545a55533d65d8e2cbba2a7b8d0d04dd1101db40352","source":{"kind":"arxiv","id":"2310.00837","version":1},"attestation_state":"computed","paper":{"title":"Helios: An Efficient Out-of-core GNN Training System on Terabyte-scale Graphs with In-memory Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Fei Wu, Jie Sun, Jie Zhang, Jun Xie, Mo Sun, Zeke Wang, Zheng Zhang, Zihan Yang, Zuocheng Shi","submitted_at":"2023-10-02T01:07:33Z","abstract_excerpt":"Training graph neural networks (GNNs) on large-scale graph data holds immense promise for numerous real-world applications but remains a great challenge. Several disk-based GNN systems have been built to train large-scale graphs in a single machine. However, they often fall short in terms of performance, especially when training on terabyte-scale graphs. This is because existing disk-based systems either overly focus on minimizing the number of SSD accesses or do not fully overlap SSD accesses with GNN training, thus resulting in substantial unnecessary overhead on the CPU side and then low GP"},"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":"2310.00837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-02T01:07:33Z","cross_cats_sorted":[],"title_canon_sha256":"5e3582be392decd69554d6989d19d361def10ae3df567d8edfdd62ed3ba312d7","abstract_canon_sha256":"912d80367026998131041f3a6d84879ed08ed60afa26b0f6a8c2142c69a34b39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:11.198329Z","signature_b64":"bEViIDC6/AMCHUt0u3FP7qvMnoFtFBt5ZQNz6L4x7hgCxni/8j52nZxUwgersEohxggXS8FeQG3WmHJ7ASCkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d69aa721007aee716311d545a55533d65d8e2cbba2a7b8d0d04dd1101db40352","last_reissued_at":"2026-07-05T06:56:11.197839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:11.197839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Helios: An Efficient Out-of-core GNN Training System on Terabyte-scale Graphs with In-memory Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Fei Wu, Jie Sun, Jie Zhang, Jun Xie, Mo Sun, Zeke Wang, Zheng Zhang, Zihan Yang, Zuocheng Shi","submitted_at":"2023-10-02T01:07:33Z","abstract_excerpt":"Training graph neural networks (GNNs) on large-scale graph data holds immense promise for numerous real-world applications but remains a great challenge. Several disk-based GNN systems have been built to train large-scale graphs in a single machine. However, they often fall short in terms of performance, especially when training on terabyte-scale graphs. This is because existing disk-based systems either overly focus on minimizing the number of SSD accesses or do not fully overlap SSD accesses with GNN training, thus resulting in substantial unnecessary overhead on the CPU side and then low GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00837","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/2310.00837/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":"2310.00837","created_at":"2026-07-05T06:56:11.197901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00837v1","created_at":"2026-07-05T06:56:11.197901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00837","created_at":"2026-07-05T06:56:11.197901+00:00"},{"alias_kind":"pith_short_12","alias_value":"22NKOIIAPLXH","created_at":"2026-07-05T06:56:11.197901+00:00"},{"alias_kind":"pith_short_16","alias_value":"22NKOIIAPLXHCYYR","created_at":"2026-07-05T06:56:11.197901+00:00"},{"alias_kind":"pith_short_8","alias_value":"22NKOIIA","created_at":"2026-07-05T06:56:11.197901+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/22NKOIIAPLXHCYYR2VC2KVJT2Z","json":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z.json","graph_json":"https://pith.science/api/pith-number/22NKOIIAPLXHCYYR2VC2KVJT2Z/graph.json","events_json":"https://pith.science/api/pith-number/22NKOIIAPLXHCYYR2VC2KVJT2Z/events.json","paper":"https://pith.science/paper/22NKOIIA"},"agent_actions":{"view_html":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z","download_json":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z.json","view_paper":"https://pith.science/paper/22NKOIIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00837&json=true","fetch_graph":"https://pith.science/api/pith-number/22NKOIIAPLXHCYYR2VC2KVJT2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/22NKOIIAPLXHCYYR2VC2KVJT2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z/action/storage_attestation","attest_author":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z/action/author_attestation","sign_citation":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z/action/citation_signature","submit_replication":"https://pith.science/pith/22NKOIIAPLXHCYYR2VC2KVJT2Z/action/replication_record"}},"created_at":"2026-07-05T06:56:11.197901+00:00","updated_at":"2026-07-05T06:56:11.197901+00:00"}