{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YSXNJALB5XCJMAVK2LSZIN5HEE","short_pith_number":"pith:YSXNJALB","schema_version":"1.0","canonical_sha256":"c4aed48161edc49602aad2e59437a72119865ec4115a0f95c8f6fffcf61f149f","source":{"kind":"arxiv","id":"2309.00738","version":3},"attestation_state":"computed","paper":{"title":"Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Cruchaga, Fuhai Li, Michael A Province, Muhan Zhang, Philip R.O. Payne, Tianyu Zhao, Yixin Chen, Zehao Dong","submitted_at":"2023-09-01T21:23:04Z","abstract_excerpt":"The expressivity of Graph Neural Networks (GNNs) has been studied broadly in recent years to reveal the design principles for more powerful GNNs. Graph canonization is known as a typical approach to distinguish non-isomorphic graphs, yet rarely adopted when developing expressive GNNs. This paper proposes to maximize the expressivity of GNNs by graph canonization, then the power of such GNNs is studies from the perspective of model stability. A stable GNN will map similar graphs to close graph representations in the vectorial space, and the stability of GNNs is critical to generalize their perf"},"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":"2309.00738","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-01T21:23:04Z","cross_cats_sorted":[],"title_canon_sha256":"47fb74414ce7925f755bc66dfc20727980ce67d00202f91b19f5ed982dd6f743","abstract_canon_sha256":"1d9a77a86edd481567c3743a08251cf4fcf41f968a57a90681e68369b1a70061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:11.207651Z","signature_b64":"hmIJYBhQBq8AtLeG4mciWX4nYilziVfYhNp9Nlxyj+tAQ/nrxSBL5QwayGghahM3JGOkQST4HG1VjB2EDaHWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4aed48161edc49602aad2e59437a72119865ec4115a0f95c8f6fffcf61f149f","last_reissued_at":"2026-07-05T07:43:11.207206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:11.207206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Cruchaga, Fuhai Li, Michael A Province, Muhan Zhang, Philip R.O. Payne, Tianyu Zhao, Yixin Chen, Zehao Dong","submitted_at":"2023-09-01T21:23:04Z","abstract_excerpt":"The expressivity of Graph Neural Networks (GNNs) has been studied broadly in recent years to reveal the design principles for more powerful GNNs. Graph canonization is known as a typical approach to distinguish non-isomorphic graphs, yet rarely adopted when developing expressive GNNs. This paper proposes to maximize the expressivity of GNNs by graph canonization, then the power of such GNNs is studies from the perspective of model stability. A stable GNN will map similar graphs to close graph representations in the vectorial space, and the stability of GNNs is critical to generalize their perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00738","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/2309.00738/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":"2309.00738","created_at":"2026-07-05T07:43:11.207262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00738v3","created_at":"2026-07-05T07:43:11.207262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00738","created_at":"2026-07-05T07:43:11.207262+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSXNJALB5XCJ","created_at":"2026-07-05T07:43:11.207262+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSXNJALB5XCJMAVK","created_at":"2026-07-05T07:43:11.207262+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSXNJALB","created_at":"2026-07-05T07:43:11.207262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15405","citing_title":"HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE","json":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE.json","graph_json":"https://pith.science/api/pith-number/YSXNJALB5XCJMAVK2LSZIN5HEE/graph.json","events_json":"https://pith.science/api/pith-number/YSXNJALB5XCJMAVK2LSZIN5HEE/events.json","paper":"https://pith.science/paper/YSXNJALB"},"agent_actions":{"view_html":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE","download_json":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE.json","view_paper":"https://pith.science/paper/YSXNJALB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00738&json=true","fetch_graph":"https://pith.science/api/pith-number/YSXNJALB5XCJMAVK2LSZIN5HEE/graph.json","fetch_events":"https://pith.science/api/pith-number/YSXNJALB5XCJMAVK2LSZIN5HEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE/action/storage_attestation","attest_author":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE/action/author_attestation","sign_citation":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE/action/citation_signature","submit_replication":"https://pith.science/pith/YSXNJALB5XCJMAVK2LSZIN5HEE/action/replication_record"}},"created_at":"2026-07-05T07:43:11.207262+00:00","updated_at":"2026-07-05T07:43:11.207262+00:00"}