{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:67YO6BML2RXUIZHYQI7Z5LB346","short_pith_number":"pith:67YO6BML","schema_version":"1.0","canonical_sha256":"f7f0ef058bd46f4464f8823f9eac3be78920856fe95fc389962ac088d8acbb9b","source":{"kind":"arxiv","id":"2301.09505","version":3},"attestation_state":"computed","paper":{"title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Di He, Liwei Wang, Shengjie Luo","submitted_at":"2023-01-23T15:58:59Z","abstract_excerpt":"Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman (WL) test, generally there is still a lack of deep understanding of what additional power they can systematically and provably gain. In this paper, we take a fundamentally different perspective to study the expressive power of GNNs beyond the WL test. Specifically, we introduce a novel class of expressivity metrics via graph biconnectivity and highlight their importance in both theory and practice."},"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":"2301.09505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-23T15:58:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"baa6bbb4ed66ce4e43003e6b5e50c779c93ee7a2fdc254c6898b8e5447ad96c0","abstract_canon_sha256":"554e90915b1d54604b95a2a539c365187733ba751a8edf1ed92fc488534a6947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:30.106224Z","signature_b64":"DVheGVDjgB1K1aQ1Z5ORm9dd1daTLgxNopgsRhQyvgZA1qLlsovmRg4WO9CB+riTfsmdDuvwkr23Vu7qWlErCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7f0ef058bd46f4464f8823f9eac3be78920856fe95fc389962ac088d8acbb9b","last_reissued_at":"2026-07-05T07:43:30.105689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:30.105689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Di He, Liwei Wang, Shengjie Luo","submitted_at":"2023-01-23T15:58:59Z","abstract_excerpt":"Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman (WL) test, generally there is still a lack of deep understanding of what additional power they can systematically and provably gain. In this paper, we take a fundamentally different perspective to study the expressive power of GNNs beyond the WL test. Specifically, we introduce a novel class of expressivity metrics via graph biconnectivity and highlight their importance in both theory and practice."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09505","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/2301.09505/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":"2301.09505","created_at":"2026-07-05T07:43:30.105767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09505v3","created_at":"2026-07-05T07:43:30.105767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09505","created_at":"2026-07-05T07:43:30.105767+00:00"},{"alias_kind":"pith_short_12","alias_value":"67YO6BML2RXU","created_at":"2026-07-05T07:43:30.105767+00:00"},{"alias_kind":"pith_short_16","alias_value":"67YO6BML2RXUIZHY","created_at":"2026-07-05T07:43:30.105767+00:00"},{"alias_kind":"pith_short_8","alias_value":"67YO6BML","created_at":"2026-07-05T07:43:30.105767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346","json":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346.json","graph_json":"https://pith.science/api/pith-number/67YO6BML2RXUIZHYQI7Z5LB346/graph.json","events_json":"https://pith.science/api/pith-number/67YO6BML2RXUIZHYQI7Z5LB346/events.json","paper":"https://pith.science/paper/67YO6BML"},"agent_actions":{"view_html":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346","download_json":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346.json","view_paper":"https://pith.science/paper/67YO6BML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09505&json=true","fetch_graph":"https://pith.science/api/pith-number/67YO6BML2RXUIZHYQI7Z5LB346/graph.json","fetch_events":"https://pith.science/api/pith-number/67YO6BML2RXUIZHYQI7Z5LB346/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346/action/storage_attestation","attest_author":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346/action/author_attestation","sign_citation":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346/action/citation_signature","submit_replication":"https://pith.science/pith/67YO6BML2RXUIZHYQI7Z5LB346/action/replication_record"}},"created_at":"2026-07-05T07:43:30.105767+00:00","updated_at":"2026-07-05T07:43:30.105767+00:00"}