{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:45IE4TJYZORMSJMQLLCWEEUHT7","short_pith_number":"pith:45IE4TJY","schema_version":"1.0","canonical_sha256":"e7504e4d38cba2c925905ac56212879fc1b2fe56114c97b77a797c862cf75a3d","source":{"kind":"arxiv","id":"1710.10035","version":2},"attestation_state":"computed","paper":{"title":"Convolutional neural networks on irregular domains based on approximate vertex-domain translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DM","authors_text":"Bastien Pasdeloup, Dominique Pastor, Jean-Charles Vialatte, Pascal Frossard, Vincent Gripon","submitted_at":"2017-10-27T09:08:29Z","abstract_excerpt":"We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are designed by translating a convolutional kernel over all pixels, thus enforcing translation equivariance. In the case of general graphs however, translation is not a well-defined operation, which makes shifting a convolutional kernel not straightforward. In this article, we introduce a methodology to allow the design of convolutional layers that are adapted to signals evolving on irr"},"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":"1710.10035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DM","submitted_at":"2017-10-27T09:08:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9208f782be1d7129f8b0e21912bdf70f09230258a92f4967e0f85dd971b9331a","abstract_canon_sha256":"153cfd7a4e3fe24aafc5faad3f5bf783dcdbab6fa78fb6b88de72d631db0a7a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:38.905211Z","signature_b64":"caKoS5eEuOcybFu6iQgUJ9wHkdP49u5EIn/4lNRJGpKO/+iw/ok6Aga1n5AtECb3G3vnRsmJeeXc4NKWgUM3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7504e4d38cba2c925905ac56212879fc1b2fe56114c97b77a797c862cf75a3d","last_reissued_at":"2026-05-18T00:01:38.904712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:38.904712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional neural networks on irregular domains based on approximate vertex-domain translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DM","authors_text":"Bastien Pasdeloup, Dominique Pastor, Jean-Charles Vialatte, Pascal Frossard, Vincent Gripon","submitted_at":"2017-10-27T09:08:29Z","abstract_excerpt":"We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are designed by translating a convolutional kernel over all pixels, thus enforcing translation equivariance. In the case of general graphs however, translation is not a well-defined operation, which makes shifting a convolutional kernel not straightforward. In this article, we introduce a methodology to allow the design of convolutional layers that are adapted to signals evolving on irr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10035","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":""},"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":"1710.10035","created_at":"2026-05-18T00:01:38.904787+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10035v2","created_at":"2026-05-18T00:01:38.904787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10035","created_at":"2026-05-18T00:01:38.904787+00:00"},{"alias_kind":"pith_short_12","alias_value":"45IE4TJYZORM","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"45IE4TJYZORMSJMQ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"45IE4TJY","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7","json":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7.json","graph_json":"https://pith.science/api/pith-number/45IE4TJYZORMSJMQLLCWEEUHT7/graph.json","events_json":"https://pith.science/api/pith-number/45IE4TJYZORMSJMQLLCWEEUHT7/events.json","paper":"https://pith.science/paper/45IE4TJY"},"agent_actions":{"view_html":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7","download_json":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7.json","view_paper":"https://pith.science/paper/45IE4TJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10035&json=true","fetch_graph":"https://pith.science/api/pith-number/45IE4TJYZORMSJMQLLCWEEUHT7/graph.json","fetch_events":"https://pith.science/api/pith-number/45IE4TJYZORMSJMQLLCWEEUHT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7/action/storage_attestation","attest_author":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7/action/author_attestation","sign_citation":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7/action/citation_signature","submit_replication":"https://pith.science/pith/45IE4TJYZORMSJMQLLCWEEUHT7/action/replication_record"}},"created_at":"2026-05-18T00:01:38.904787+00:00","updated_at":"2026-05-18T00:01:38.904787+00:00"}