{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VMTKM7CYUQDK6PLPXSXZQ4JUR2","short_pith_number":"pith:VMTKM7CY","schema_version":"1.0","canonical_sha256":"ab26a67c58a406af3d6fbcaf9871348eb3c74216ebe2f8ac1d999389e2bf850c","source":{"kind":"arxiv","id":"1810.02244","version":5},"attestation_state":"computed","paper":{"title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Gaurav Rattan, Jan Eric Lenssen, Martin Grohe, Martin Ritzert, Matthias Fey, William L. Hamilton","submitted_at":"2018-10-04T14:31:57Z","abstract_excerpt":"In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical point of view and relates them to the $1$-dimensional Weisfeiler-Leman graph isomorphism heuristic ($1$-WL). We show that GNNs have the same expressiveness as the $1$-WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcoming"},"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":"1810.02244","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T14:31:57Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"1201cc1943771f02c50da19304e240a9952b833e48f637d399742e8fcc1dc0ce","abstract_canon_sha256":"81560e00bef5943d7ca17cc4f0dc0f2b3f9cc22621032a0c28018583da5abf10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:56.975100Z","signature_b64":"q+CKbbuqlOuWIacRKZmo4zf/Gztp1y3qI4Kh02KD/OzznRw5owsRAELapvOKnG67hM08Hj3jSDvkE0MWx5hmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab26a67c58a406af3d6fbcaf9871348eb3c74216ebe2f8ac1d999389e2bf850c","last_reissued_at":"2026-07-05T03:35:56.974690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:56.974690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Morris, Gaurav Rattan, Jan Eric Lenssen, Martin Grohe, Martin Ritzert, Matthias Fey, William L. Hamilton","submitted_at":"2018-10-04T14:31:57Z","abstract_excerpt":"In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical point of view and relates them to the $1$-dimensional Weisfeiler-Leman graph isomorphism heuristic ($1$-WL). We show that GNNs have the same expressiveness as the $1$-WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcoming"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02244","kind":"arxiv","version":5},"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/1810.02244/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":"1810.02244","created_at":"2026-07-05T03:35:56.974748+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02244v5","created_at":"2026-07-05T03:35:56.974748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02244","created_at":"2026-07-05T03:35:56.974748+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMTKM7CYUQDK","created_at":"2026-07-05T03:35:56.974748+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMTKM7CYUQDK6PLP","created_at":"2026-07-05T03:35:56.974748+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMTKM7CY","created_at":"2026-07-05T03:35:56.974748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.08990","citing_title":"Spectral-based Graph Convolutional Network for Directed Graphs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07828","citing_title":"NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07828","citing_title":"NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2","json":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2.json","graph_json":"https://pith.science/api/pith-number/VMTKM7CYUQDK6PLPXSXZQ4JUR2/graph.json","events_json":"https://pith.science/api/pith-number/VMTKM7CYUQDK6PLPXSXZQ4JUR2/events.json","paper":"https://pith.science/paper/VMTKM7CY"},"agent_actions":{"view_html":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2","download_json":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2.json","view_paper":"https://pith.science/paper/VMTKM7CY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/VMTKM7CYUQDK6PLPXSXZQ4JUR2/graph.json","fetch_events":"https://pith.science/api/pith-number/VMTKM7CYUQDK6PLPXSXZQ4JUR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2/action/storage_attestation","attest_author":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2/action/author_attestation","sign_citation":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2/action/citation_signature","submit_replication":"https://pith.science/pith/VMTKM7CYUQDK6PLPXSXZQ4JUR2/action/replication_record"}},"created_at":"2026-07-05T03:35:56.974748+00:00","updated_at":"2026-07-05T03:35:56.974748+00:00"}