{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UKBHKCLJEPFMZHA7BG3JJGYRCQ","short_pith_number":"pith:UKBHKCLJ","schema_version":"1.0","canonical_sha256":"a28275096923cacc9c1f09b6949b11141c3ede702fc7477498f3b76155c4c2a7","source":{"kind":"arxiv","id":"1907.12972","version":3},"attestation_state":"computed","paper":{"title":"Transferability of Spectral Graph Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gitta Kutyniok, Lorenzo Bucci, Michael M. Bronstein, Ron Levie, Wei Huang","submitted_at":"2019-07-30T14:16:45Z","abstract_excerpt":"This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals defined on many different graphs, the trained ConvNet should generalize to signals on graphs unseen in the training set. It is thus important to transfer ConvNets between graphs. Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet s"},"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":"1907.12972","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T14:16:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"66a080409202a083edd3052e768aad8fb920bfbfc06e1c8ed62eb207ed68d58c","abstract_canon_sha256":"b1b8fb24d06f05b90ca2d867ee417c5c54472bb284cb9209e312a12e83557efc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:32.162221Z","signature_b64":"kAcRn01FlyFQOvVSlHllOD+THIs6ypOhqLzVOWT0WjGTlSObKcW58LpnYBpBrfmsSqKNPur66Radd8CQsJcmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a28275096923cacc9c1f09b6949b11141c3ede702fc7477498f3b76155c4c2a7","last_reissued_at":"2026-07-05T02:48:32.161764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:32.161764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferability of Spectral Graph Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gitta Kutyniok, Lorenzo Bucci, Michael M. Bronstein, Ron Levie, Wei Huang","submitted_at":"2019-07-30T14:16:45Z","abstract_excerpt":"This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals defined on many different graphs, the trained ConvNet should generalize to signals on graphs unseen in the training set. It is thus important to transfer ConvNets between graphs. Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12972","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/1907.12972/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":"1907.12972","created_at":"2026-07-05T02:48:32.161820+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.12972v3","created_at":"2026-07-05T02:48:32.161820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12972","created_at":"2026-07-05T02:48:32.161820+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKBHKCLJEPFM","created_at":"2026-07-05T02:48:32.161820+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKBHKCLJEPFMZHA7","created_at":"2026-07-05T02:48:32.161820+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKBHKCLJ","created_at":"2026-07-05T02:48:32.161820+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":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ","json":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ.json","graph_json":"https://pith.science/api/pith-number/UKBHKCLJEPFMZHA7BG3JJGYRCQ/graph.json","events_json":"https://pith.science/api/pith-number/UKBHKCLJEPFMZHA7BG3JJGYRCQ/events.json","paper":"https://pith.science/paper/UKBHKCLJ"},"agent_actions":{"view_html":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ","download_json":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ.json","view_paper":"https://pith.science/paper/UKBHKCLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.12972&json=true","fetch_graph":"https://pith.science/api/pith-number/UKBHKCLJEPFMZHA7BG3JJGYRCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UKBHKCLJEPFMZHA7BG3JJGYRCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ/action/storage_attestation","attest_author":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ/action/author_attestation","sign_citation":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ/action/citation_signature","submit_replication":"https://pith.science/pith/UKBHKCLJEPFMZHA7BG3JJGYRCQ/action/replication_record"}},"created_at":"2026-07-05T02:48:32.161820+00:00","updated_at":"2026-07-05T02:48:32.161820+00:00"}