{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REYZVHEEMOX5N4KPSETUESJAWG","short_pith_number":"pith:REYZVHEE","schema_version":"1.0","canonical_sha256":"89319a9c8463afd6f14f9127424920b1b689e8f7cb8af0f03a5ee6780faf9d5d","source":{"kind":"arxiv","id":"2408.12334","version":2},"attestation_state":"computed","paper":{"title":"Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Horst Bischof, Niloofar Azizi, Nils Kriege","submitted_at":"2024-08-22T12:22:00Z","abstract_excerpt":"Graph Neural Networks (GNNs) excel in handling graph-structured data but often underperform in link prediction tasks compared to classical methods, mainly due to the limitations of the commonly used message-passing principle. Notably, their ability to distinguish non-isomorphic graphs is limited by the 1-dimensional Weisfeiler-Lehman test. Our study presents a novel method to enhance the expressivity of GNNs by embedding induced subgraphs into the graph Laplacian matrix's eigenbasis. We introduce a Learnable Lanczos algorithm with Linear Constraints (LLwLC), proposing two novel subgraph extrac"},"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":"2408.12334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T12:22:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3502b0da906e7fdfc701cff563e59f4484b4160fc4f5f4a6d4c9fd9cfba95498","abstract_canon_sha256":"b8c961e037fb67e2becab6a2dcbb13a140d4745b3940f97326d611e044a6cc3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:44.881401Z","signature_b64":"jccEY+IgFuAaW+Hk8S5XluSEtJ83ICCY6E8dTdD3OQMzx7XvJUs5UX0QoD5Q6NCDN9/Hs+uIE8XbGC9EvbQuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89319a9c8463afd6f14f9127424920b1b689e8f7cb8af0f03a5ee6780faf9d5d","last_reissued_at":"2026-07-05T10:14:44.880896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:44.880896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Horst Bischof, Niloofar Azizi, Nils Kriege","submitted_at":"2024-08-22T12:22:00Z","abstract_excerpt":"Graph Neural Networks (GNNs) excel in handling graph-structured data but often underperform in link prediction tasks compared to classical methods, mainly due to the limitations of the commonly used message-passing principle. Notably, their ability to distinguish non-isomorphic graphs is limited by the 1-dimensional Weisfeiler-Lehman test. Our study presents a novel method to enhance the expressivity of GNNs by embedding induced subgraphs into the graph Laplacian matrix's eigenbasis. We introduce a Learnable Lanczos algorithm with Linear Constraints (LLwLC), proposing two novel subgraph extrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12334","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/2408.12334/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":"2408.12334","created_at":"2026-07-05T10:14:44.880950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12334v2","created_at":"2026-07-05T10:14:44.880950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12334","created_at":"2026-07-05T10:14:44.880950+00:00"},{"alias_kind":"pith_short_12","alias_value":"REYZVHEEMOX5","created_at":"2026-07-05T10:14:44.880950+00:00"},{"alias_kind":"pith_short_16","alias_value":"REYZVHEEMOX5N4KP","created_at":"2026-07-05T10:14:44.880950+00:00"},{"alias_kind":"pith_short_8","alias_value":"REYZVHEE","created_at":"2026-07-05T10:14:44.880950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02479","citing_title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG","json":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG.json","graph_json":"https://pith.science/api/pith-number/REYZVHEEMOX5N4KPSETUESJAWG/graph.json","events_json":"https://pith.science/api/pith-number/REYZVHEEMOX5N4KPSETUESJAWG/events.json","paper":"https://pith.science/paper/REYZVHEE"},"agent_actions":{"view_html":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG","download_json":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG.json","view_paper":"https://pith.science/paper/REYZVHEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12334&json=true","fetch_graph":"https://pith.science/api/pith-number/REYZVHEEMOX5N4KPSETUESJAWG/graph.json","fetch_events":"https://pith.science/api/pith-number/REYZVHEEMOX5N4KPSETUESJAWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG/action/storage_attestation","attest_author":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG/action/author_attestation","sign_citation":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG/action/citation_signature","submit_replication":"https://pith.science/pith/REYZVHEEMOX5N4KPSETUESJAWG/action/replication_record"}},"created_at":"2026-07-05T10:14:44.880950+00:00","updated_at":"2026-07-05T10:14:44.880950+00:00"}