{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZXWBTKDHWEIBCXV64EJP7AGDB7","short_pith_number":"pith:ZXWBTKDH","schema_version":"1.0","canonical_sha256":"cdec19a867b110115ebee112ff80c30fc6d6f61da7b78fb0f81f03fa03638bfc","source":{"kind":"arxiv","id":"2103.09430","version":3},"attestation_state":"computed","paper":{"title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyu Ren, Jure Leskovec, Maho Nakata, Matthias Fey, Weihua Hu, Yuxiao Dong","submitted_at":"2021-03-17T04:08:03Z","abstract_excerpt":"Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications. However, existing efforts to advance large-scale graph ML have been largely limited by the lack of a suitable public benchmark. Here we present OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for facilitating the advancements in large-scale graph ML. The OGB-LSC datasets are orders of magnitude larger than existing ones, covering three core graph learning tasks -- link pred"},"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":"2103.09430","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-17T04:08:03Z","cross_cats_sorted":[],"title_canon_sha256":"124d37e58a74f51d844c6c0088513dbca7dbcd7adf9884241396910d5d0f1a66","abstract_canon_sha256":"774052a857dc5152fd6d3051b74c3af622b9e4833f4d1c7a90cc87bdc10310f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:28.739334Z","signature_b64":"bjaBYKAQB5D6EVjiA9YxOoQF7xlh8GqHsrpxXnzpeTuyv0XzKMkdAF1CWEovpQm8boH7FrJREJzemsc2+7UOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdec19a867b110115ebee112ff80c30fc6d6f61da7b78fb0f81f03fa03638bfc","last_reissued_at":"2026-07-05T03:24:28.738833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:28.738833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyu Ren, Jure Leskovec, Maho Nakata, Matthias Fey, Weihua Hu, Yuxiao Dong","submitted_at":"2021-03-17T04:08:03Z","abstract_excerpt":"Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications. However, existing efforts to advance large-scale graph ML have been largely limited by the lack of a suitable public benchmark. Here we present OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for facilitating the advancements in large-scale graph ML. The OGB-LSC datasets are orders of magnitude larger than existing ones, covering three core graph learning tasks -- link pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09430","kind":"arxiv","version":3},"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/2103.09430/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":"2103.09430","created_at":"2026-07-05T03:24:28.738893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09430v3","created_at":"2026-07-05T03:24:28.738893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09430","created_at":"2026-07-05T03:24:28.738893+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXWBTKDHWEIB","created_at":"2026-07-05T03:24:28.738893+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXWBTKDHWEIBCXV6","created_at":"2026-07-05T03:24:28.738893+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXWBTKDH","created_at":"2026-07-05T03:24:28.738893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17667","citing_title":"Handling Feature Heterogeneity with Learnable Graph Patches","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11898","citing_title":"GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03232","citing_title":"GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00808","citing_title":"Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17656","citing_title":"Pretraining a Foundation Model for Small-Molecule Natural Products","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18387","citing_title":"Graph Hierarchical Recurrence for Long-Range Generalization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18211","citing_title":"Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00656","citing_title":"DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17071","citing_title":"AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03361","citing_title":"The limits of bio-molecular modeling with large language models : a cross-scale evaluation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03154","citing_title":"DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12161","citing_title":"Fused Gromov-Wasserstein Distance with Feature Selection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23758","citing_title":"Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7","json":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7.json","graph_json":"https://pith.science/api/pith-number/ZXWBTKDHWEIBCXV64EJP7AGDB7/graph.json","events_json":"https://pith.science/api/pith-number/ZXWBTKDHWEIBCXV64EJP7AGDB7/events.json","paper":"https://pith.science/paper/ZXWBTKDH"},"agent_actions":{"view_html":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7","download_json":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7.json","view_paper":"https://pith.science/paper/ZXWBTKDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09430&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXWBTKDHWEIBCXV64EJP7AGDB7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXWBTKDHWEIBCXV64EJP7AGDB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7/action/storage_attestation","attest_author":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7/action/author_attestation","sign_citation":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7/action/citation_signature","submit_replication":"https://pith.science/pith/ZXWBTKDHWEIBCXV64EJP7AGDB7/action/replication_record"}},"created_at":"2026-07-05T03:24:28.738893+00:00","updated_at":"2026-07-05T03:24:28.738893+00:00"}