{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O4QJ4TE7FE47SNM47SFPNKB2DF","short_pith_number":"pith:O4QJ4TE7","schema_version":"1.0","canonical_sha256":"77209e4c9f2939f9359cfc8af6a83a1971dbd6e5b972f18167c69488c1af27fd","source":{"kind":"arxiv","id":"2101.10320","version":2},"attestation_state":"computed","paper":{"title":"Identity-aware Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Jiaxuan You, Jonathan Gomes-Selman, Jure Leskovec, Rex Ying","submitted_at":"2021-01-25T18:59:01Z","abstract_excerpt":"Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitat"},"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":"2101.10320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-25T18:59:01Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"63e71b41872035a3dbf3a22d90ac7d12e9eec4627a58cdac3f7421dccc9d3654","abstract_canon_sha256":"d2aaa91f59e658c813fa4b44ff0154918707a002460aa197a1500dbf53e34803"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:04.854283Z","signature_b64":"NWFU0xk/2K4v5vp2pxw8ttijU5M5g4wkmdqHj3jx9LvZ+0HJlZiwLImk7SzExwUrjhL6IgynkHVOiflNZBB1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77209e4c9f2939f9359cfc8af6a83a1971dbd6e5b972f18167c69488c1af27fd","last_reissued_at":"2026-07-05T02:13:04.853851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:04.853851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identity-aware Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Jiaxuan You, Jonathan Gomes-Selman, Jure Leskovec, Rex Ying","submitted_at":"2021-01-25T18:59:01Z","abstract_excerpt":"Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10320","kind":"arxiv","version":2},"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/2101.10320/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":"2101.10320","created_at":"2026-07-05T02:13:04.853917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10320v2","created_at":"2026-07-05T02:13:04.853917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10320","created_at":"2026-07-05T02:13:04.853917+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4QJ4TE7FE47","created_at":"2026-07-05T02:13:04.853917+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4QJ4TE7FE47SNM4","created_at":"2026-07-05T02:13:04.853917+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4QJ4TE7","created_at":"2026-07-05T02:13:04.853917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05063","citing_title":"Computing and Learning on Combinatorial Data","ref_index":220,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF","json":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF.json","graph_json":"https://pith.science/api/pith-number/O4QJ4TE7FE47SNM47SFPNKB2DF/graph.json","events_json":"https://pith.science/api/pith-number/O4QJ4TE7FE47SNM47SFPNKB2DF/events.json","paper":"https://pith.science/paper/O4QJ4TE7"},"agent_actions":{"view_html":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF","download_json":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF.json","view_paper":"https://pith.science/paper/O4QJ4TE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10320&json=true","fetch_graph":"https://pith.science/api/pith-number/O4QJ4TE7FE47SNM47SFPNKB2DF/graph.json","fetch_events":"https://pith.science/api/pith-number/O4QJ4TE7FE47SNM47SFPNKB2DF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF/action/storage_attestation","attest_author":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF/action/author_attestation","sign_citation":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF/action/citation_signature","submit_replication":"https://pith.science/pith/O4QJ4TE7FE47SNM47SFPNKB2DF/action/replication_record"}},"created_at":"2026-07-05T02:13:04.853917+00:00","updated_at":"2026-07-05T02:13:04.853917+00:00"}