{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OROCPU55TBRPS77J6VI2EY3DAC","short_pith_number":"pith:OROCPU55","schema_version":"1.0","canonical_sha256":"745c27d3bd9862f97fe9f551a2636300a295d61e1849c3fee117c5d5729865ee","source":{"kind":"arxiv","id":"1911.06253","version":5},"attestation_state":"computed","paper":{"title":"Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Tong, Feng Gao, Guy Wolf, Matthew Hirn, Michael Perlmutter","submitted_at":"2019-11-14T17:23:06Z","abstract_excerpt":"The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transform for non-Euclidean settings such as graphs. Our work builds upon these constructions by introducing windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts. As a result, the "},"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":"1911.06253","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-14T17:23:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7af07bb6273d1a99e162480321e6f6f4de314cf03e490a65223730e49bd2cfe","abstract_canon_sha256":"596fa67deb34f7d77f184269cd2aa7d74d1c59817f6660cbcb0f2e1bbd8bf3d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:56.175734Z","signature_b64":"o8EA/sPJM1Lgp3I4uaLd1V1KwcOdlk1rtBG8flbv2BJMgmwa3T5eODBH/nVsCQmjAXmhsxAkZ/mxGpjRemB+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"745c27d3bd9862f97fe9f551a2636300a295d61e1849c3fee117c5d5729865ee","last_reissued_at":"2026-07-05T06:25:56.175256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:56.175256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Tong, Feng Gao, Guy Wolf, Matthew Hirn, Michael Perlmutter","submitted_at":"2019-11-14T17:23:06Z","abstract_excerpt":"The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transform for non-Euclidean settings such as graphs. Our work builds upon these constructions by introducing windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts. As a result, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06253","kind":"arxiv","version":5},"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/1911.06253/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":"1911.06253","created_at":"2026-07-05T06:25:56.175319+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06253v5","created_at":"2026-07-05T06:25:56.175319+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06253","created_at":"2026-07-05T06:25:56.175319+00:00"},{"alias_kind":"pith_short_12","alias_value":"OROCPU55TBRP","created_at":"2026-07-05T06:25:56.175319+00:00"},{"alias_kind":"pith_short_16","alias_value":"OROCPU55TBRPS77J","created_at":"2026-07-05T06:25:56.175319+00:00"},{"alias_kind":"pith_short_8","alias_value":"OROCPU55","created_at":"2026-07-05T06:25:56.175319+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":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC","json":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC.json","graph_json":"https://pith.science/api/pith-number/OROCPU55TBRPS77J6VI2EY3DAC/graph.json","events_json":"https://pith.science/api/pith-number/OROCPU55TBRPS77J6VI2EY3DAC/events.json","paper":"https://pith.science/paper/OROCPU55"},"agent_actions":{"view_html":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC","download_json":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC.json","view_paper":"https://pith.science/paper/OROCPU55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06253&json=true","fetch_graph":"https://pith.science/api/pith-number/OROCPU55TBRPS77J6VI2EY3DAC/graph.json","fetch_events":"https://pith.science/api/pith-number/OROCPU55TBRPS77J6VI2EY3DAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC/action/storage_attestation","attest_author":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC/action/author_attestation","sign_citation":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC/action/citation_signature","submit_replication":"https://pith.science/pith/OROCPU55TBRPS77J6VI2EY3DAC/action/replication_record"}},"created_at":"2026-07-05T06:25:56.175319+00:00","updated_at":"2026-07-05T06:25:56.175319+00:00"}