{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4JCNKJUMCIYLF4JHJ63YNGGFOH","short_pith_number":"pith:4JCNKJUM","schema_version":"1.0","canonical_sha256":"e244d5268c1230b2f1274fb78698c571c1973aa4ba255e0d3ede0978224c4ef7","source":{"kind":"arxiv","id":"2109.10096","version":2},"attestation_state":"computed","paper":{"title":"Transferability of Graph Neural Networks: an Extended Graphon Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Gitta Kutyniok, Ron Levie, Sohir Maskey","submitted_at":"2021-09-21T10:59:01Z","abstract_excerpt":"We study spectral graph convolutional neural networks (GCNNs), where filters are defined as continuous functions of the graph shift operator (GSO) through functional calculus. A spectral GCNN is not tailored to one specific graph and can be transferred between different graphs. It is hence important to study the GCNN transferability: the capacity of the network to have approximately the same repercussion on different graphs that represent the same phenomenon. Transferability ensures that GCNNs trained on certain graphs generalize if the graphs in the test set represent the same phenomena as th"},"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":"2109.10096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-21T10:59:01Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"bb6c1c1f2aa7c1ac66ee2d95a24a2d10392c19c82384f1b24d2fe7e7b16f59a8","abstract_canon_sha256":"03bf3dba3174b0a40ef345fe84fe431baa8d8f0eb34bcaa658ceefc5615cda48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:47.258928Z","signature_b64":"Y3O5C8HByTDwCmz1mq0FhH6+sNKkyj4wnTGOnUOUsXBETwwvTdtovsbMCvloJOOTnYfVWW3JO8nyhlZC/1mVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e244d5268c1230b2f1274fb78698c571c1973aa4ba255e0d3ede0978224c4ef7","last_reissued_at":"2026-07-05T04:34:47.258445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:47.258445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferability of Graph Neural Networks: an Extended Graphon Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Gitta Kutyniok, Ron Levie, Sohir Maskey","submitted_at":"2021-09-21T10:59:01Z","abstract_excerpt":"We study spectral graph convolutional neural networks (GCNNs), where filters are defined as continuous functions of the graph shift operator (GSO) through functional calculus. A spectral GCNN is not tailored to one specific graph and can be transferred between different graphs. It is hence important to study the GCNN transferability: the capacity of the network to have approximately the same repercussion on different graphs that represent the same phenomenon. Transferability ensures that GCNNs trained on certain graphs generalize if the graphs in the test set represent the same phenomena as th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10096","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/2109.10096/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":"2109.10096","created_at":"2026-07-05T04:34:47.258504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10096v2","created_at":"2026-07-05T04:34:47.258504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10096","created_at":"2026-07-05T04:34:47.258504+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JCNKJUMCIYL","created_at":"2026-07-05T04:34:47.258504+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JCNKJUMCIYLF4JH","created_at":"2026-07-05T04:34:47.258504+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JCNKJUM","created_at":"2026-07-05T04:34:47.258504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31315","citing_title":"Graph Neural Networks Are Not Continuous Across Graph Resolutions","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH","json":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH.json","graph_json":"https://pith.science/api/pith-number/4JCNKJUMCIYLF4JHJ63YNGGFOH/graph.json","events_json":"https://pith.science/api/pith-number/4JCNKJUMCIYLF4JHJ63YNGGFOH/events.json","paper":"https://pith.science/paper/4JCNKJUM"},"agent_actions":{"view_html":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH","download_json":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH.json","view_paper":"https://pith.science/paper/4JCNKJUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10096&json=true","fetch_graph":"https://pith.science/api/pith-number/4JCNKJUMCIYLF4JHJ63YNGGFOH/graph.json","fetch_events":"https://pith.science/api/pith-number/4JCNKJUMCIYLF4JHJ63YNGGFOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH/action/storage_attestation","attest_author":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH/action/author_attestation","sign_citation":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH/action/citation_signature","submit_replication":"https://pith.science/pith/4JCNKJUMCIYLF4JHJ63YNGGFOH/action/replication_record"}},"created_at":"2026-07-05T04:34:47.258504+00:00","updated_at":"2026-07-05T04:34:47.258504+00:00"}