{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4RVUBW73DTYDOSQC57TN67Y2ZI","short_pith_number":"pith:4RVUBW73","schema_version":"1.0","canonical_sha256":"e46b40dbfb1cf0374a02efe6df7f1aca2bde04bd3adab017a56f0cb2795c7dde","source":{"kind":"arxiv","id":"1911.05485","version":6},"attestation_state":"computed","paper":{"title":"Diffusion Improves Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.SI","authors_text":"Johannes Gasteiger, Stefan Wei{\\ss}enberger, Stephan G\\\"unnemann","submitted_at":"2019-10-28T17:51:46Z","abstract_excerpt":"Graph convolution is the core of most Graph Neural Networks (GNNs) and usually approximated by message passing between direct (one-hop) neighbors. In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC). GDC leverages generalized graph diffusion, examples of which are the heat kernel and personalized PageRank. It alleviates the problem of noisy and often arbitrarily defined edges in real graphs. We show that GDC is closely related to spectral-based models and thus combines"},"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":"1911.05485","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-10-28T17:51:46Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"bdc287fb1ab8ead7893eb3464733de9bfac4321626a55e6cf5162d5047e29a3e","abstract_canon_sha256":"41b5274241f4420f011b0944c657c24587cd189dc0d05b29c8640ff70235d0c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:22.384452Z","signature_b64":"LJrj+Nbe/u023HQX64h1f9azrYhhUwvJ17Ls/Mrm92Ll9fCxhjCRSY/rIQ6F+gO8Fvf7jO5Qn6aGsoLppeNGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46b40dbfb1cf0374a02efe6df7f1aca2bde04bd3adab017a56f0cb2795c7dde","last_reissued_at":"2026-07-05T04:11:22.383968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:22.383968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Improves Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.SI","authors_text":"Johannes Gasteiger, Stefan Wei{\\ss}enberger, Stephan G\\\"unnemann","submitted_at":"2019-10-28T17:51:46Z","abstract_excerpt":"Graph convolution is the core of most Graph Neural Networks (GNNs) and usually approximated by message passing between direct (one-hop) neighbors. In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC). GDC leverages generalized graph diffusion, examples of which are the heat kernel and personalized PageRank. It alleviates the problem of noisy and often arbitrarily defined edges in real graphs. We show that GDC is closely related to spectral-based models and thus combines"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05485","kind":"arxiv","version":6},"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/1911.05485/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":"1911.05485","created_at":"2026-07-05T04:11:22.384021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05485v6","created_at":"2026-07-05T04:11:22.384021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05485","created_at":"2026-07-05T04:11:22.384021+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RVUBW73DTYD","created_at":"2026-07-05T04:11:22.384021+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RVUBW73DTYDOSQC","created_at":"2026-07-05T04:11:22.384021+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RVUBW73","created_at":"2026-07-05T04:11:22.384021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08679","citing_title":"Attention-based graph neural networks: a survey","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI","json":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI.json","graph_json":"https://pith.science/api/pith-number/4RVUBW73DTYDOSQC57TN67Y2ZI/graph.json","events_json":"https://pith.science/api/pith-number/4RVUBW73DTYDOSQC57TN67Y2ZI/events.json","paper":"https://pith.science/paper/4RVUBW73"},"agent_actions":{"view_html":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI","download_json":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI.json","view_paper":"https://pith.science/paper/4RVUBW73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05485&json=true","fetch_graph":"https://pith.science/api/pith-number/4RVUBW73DTYDOSQC57TN67Y2ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/4RVUBW73DTYDOSQC57TN67Y2ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI/action/storage_attestation","attest_author":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI/action/author_attestation","sign_citation":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI/action/citation_signature","submit_replication":"https://pith.science/pith/4RVUBW73DTYDOSQC57TN67Y2ZI/action/replication_record"}},"created_at":"2026-07-05T04:11:22.384021+00:00","updated_at":"2026-07-05T04:11:22.384021+00:00"}