{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BO7S35T33Z6JTSGW3XMO7DBY4H","short_pith_number":"pith:BO7S35T3","schema_version":"1.0","canonical_sha256":"0bbf2df67bde7c99c8d6ddd8ef8c38e1d1c94e6ec1a0ee2bad0f18f906a6b46d","source":{"kind":"arxiv","id":"2007.08663","version":1},"attestation_state":"computed","paper":{"title":"TUDataset: A collection of benchmark datasets for learning with graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Franka Bause, Kristian Kersting, Marion Neumann, Nils M. Kriege, Petra Mutzel","submitted_at":"2020-07-16T21:46:33Z","abstract_excerpt":"Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging, consequently hindering advancements in this area. To address this, we introduce the TUDataset for graph classification and regression. The collection consists of over 120 datasets of varying sizes from a wide range of applications. We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools. Here, we gi"},"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":"2007.08663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-16T21:46:33Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"602f8eab31b3142a7cd4f1058554f253b166824d58d089bc9e4ab0f8ad548af4","abstract_canon_sha256":"2643d4711a7339d03fd53578b02da7b1e78571e6957f1a196a68267185d487d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T07:48:37.210265Z","signature_b64":"iGIuglKh+1rrRrfo5rfCsDOwB7cQMDgWmJSj+nEY6C9msE9+72pqzHpf3MfN69Z1namV3VY6RGyqgEGvugc7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bbf2df67bde7c99c8d6ddd8ef8c38e1d1c94e6ec1a0ee2bad0f18f906a6b46d","last_reissued_at":"2026-05-25T07:48:37.207139Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T07:48:37.207139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TUDataset: A collection of benchmark datasets for learning with graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Franka Bause, Kristian Kersting, Marion Neumann, Nils M. Kriege, Petra Mutzel","submitted_at":"2020-07-16T21:46:33Z","abstract_excerpt":"Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging, consequently hindering advancements in this area. To address this, we introduce the TUDataset for graph classification and regression. The collection consists of over 120 datasets of varying sizes from a wide range of applications. We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools. Here, we gi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08663","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/2007.08663/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":"2007.08663","created_at":"2026-05-25T07:48:37.207292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08663v1","created_at":"2026-05-25T07:48:37.207292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08663","created_at":"2026-05-25T07:48:37.207292+00:00"},{"alias_kind":"pith_short_12","alias_value":"BO7S35T33Z6J","created_at":"2026-05-25T07:48:37.207292+00:00"},{"alias_kind":"pith_short_16","alias_value":"BO7S35T33Z6JTSGW","created_at":"2026-05-25T07:48:37.207292+00:00"},{"alias_kind":"pith_short_8","alias_value":"BO7S35T3","created_at":"2026-05-25T07:48:37.207292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2508.10651","citing_title":"Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11629","citing_title":"GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2411.17429","citing_title":"Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00773","citing_title":"OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Tasks","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18893","citing_title":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08618","citing_title":"HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystals","ref_index":119,"is_internal_anchor":true},{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2512.08089","citing_title":"Efficient and Accurate Graph Classification with Hyperdimensional Computing on FPGA","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18893","citing_title":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23875","citing_title":"A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08618","citing_title":"HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystals","ref_index":119,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13383","citing_title":"Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12827","citing_title":"GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12009","citing_title":"Estimating Subgraph Importance with Structural Prior Domain Knowledge","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09099","citing_title":"GraphNetz: Statistical Benchmarking of Graph Neural Networks with Paired Tests and Rank Aggregation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09486","citing_title":"CTQWformer: A CTQW-based Transformer for Graph Classification","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09866","citing_title":"Higher-order Persistence Diagrams","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09226","citing_title":"Quantum Injection Pathways for Implicit Graph Neural Networks","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08810","citing_title":"R2G: A Multi-View Circuit Graph Benchmark Suite from RTL to GDSII","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15273","citing_title":"How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18868","citing_title":"Subgraph Concept Networks: Concept Levels in Graph Classification","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20082","citing_title":"Concept Graph Convolutions: Message Passing in the Concept Space","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02780","citing_title":"Fine-Grained Graph Generation through Latent Mixture Scheduling","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H","json":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H.json","graph_json":"https://pith.science/api/pith-number/BO7S35T33Z6JTSGW3XMO7DBY4H/graph.json","events_json":"https://pith.science/api/pith-number/BO7S35T33Z6JTSGW3XMO7DBY4H/events.json","paper":"https://pith.science/paper/BO7S35T3"},"agent_actions":{"view_html":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H","download_json":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H.json","view_paper":"https://pith.science/paper/BO7S35T3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08663&json=true","fetch_graph":"https://pith.science/api/pith-number/BO7S35T33Z6JTSGW3XMO7DBY4H/graph.json","fetch_events":"https://pith.science/api/pith-number/BO7S35T33Z6JTSGW3XMO7DBY4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H/action/storage_attestation","attest_author":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H/action/author_attestation","sign_citation":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H/action/citation_signature","submit_replication":"https://pith.science/pith/BO7S35T33Z6JTSGW3XMO7DBY4H/action/replication_record"}},"created_at":"2026-05-25T07:48:37.207292+00:00","updated_at":"2026-05-25T07:48:37.207292+00:00"}