{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M5SF3KKRGLT5CPCKX7YEF5XYRN","short_pith_number":"pith:M5SF3KKR","schema_version":"1.0","canonical_sha256":"67645da95132e7d13c4abff042f6f88b57ad497611d7c687c2e4cbda4161f730","source":{"kind":"arxiv","id":"2403.15182","version":3},"attestation_state":"computed","paper":{"title":"PDE-CNNs: Axiomatic Derivations and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bart M. N. Smets, Gijs Bellaard, Remco Duits, Sei Sakata","submitted_at":"2024-03-22T13:11:26Z","abstract_excerpt":"PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) use solvers of evolution PDEs as substitutes for the conventional components in G-CNNs. PDE-G-CNNs can offer several benefits simultaneously: fewer parameters, inherent equivariance, better accuracy, and data efficiency.\n  In this article we focus on Euclidean equivariant PDE-G-CNNs where the feature maps are two-dimensional throughout. We call this variant of the framework a PDE-CNN.\n  From a machine learning perspective, we list several practically desirable axioms and derive from these which PDEs should be used in a PDE-CNN, this be"},"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":"2403.15182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-22T13:11:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ed2d3b765e5b6e4875dfc5801fb8dbafc75ae09fb985d9aa293212950913080","abstract_canon_sha256":"e388370f34a05fcafd08c8202cb8380e544c3a9246544e2d240659ba796dea34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:52.528861Z","signature_b64":"Hupo8tTQZxaWY6MPkjyNTTp8exeiDZSdTkpLj+s6Od0WoqTsa1kkPxPT3UTgZm/Y9OrKuQ0NWdHu/h/gyRn1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67645da95132e7d13c4abff042f6f88b57ad497611d7c687c2e4cbda4161f730","last_reissued_at":"2026-07-05T09:37:52.528395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:52.528395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PDE-CNNs: Axiomatic Derivations and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bart M. N. Smets, Gijs Bellaard, Remco Duits, Sei Sakata","submitted_at":"2024-03-22T13:11:26Z","abstract_excerpt":"PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) use solvers of evolution PDEs as substitutes for the conventional components in G-CNNs. PDE-G-CNNs can offer several benefits simultaneously: fewer parameters, inherent equivariance, better accuracy, and data efficiency.\n  In this article we focus on Euclidean equivariant PDE-G-CNNs where the feature maps are two-dimensional throughout. We call this variant of the framework a PDE-CNN.\n  From a machine learning perspective, we list several practically desirable axioms and derive from these which PDEs should be used in a PDE-CNN, this be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15182","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/2403.15182/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":"2403.15182","created_at":"2026-07-05T09:37:52.528454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15182v3","created_at":"2026-07-05T09:37:52.528454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15182","created_at":"2026-07-05T09:37:52.528454+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5SF3KKRGLT5","created_at":"2026-07-05T09:37:52.528454+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5SF3KKRGLT5CPCK","created_at":"2026-07-05T09:37:52.528454+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5SF3KKR","created_at":"2026-07-05T09:37:52.528454+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/M5SF3KKRGLT5CPCKX7YEF5XYRN","json":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN.json","graph_json":"https://pith.science/api/pith-number/M5SF3KKRGLT5CPCKX7YEF5XYRN/graph.json","events_json":"https://pith.science/api/pith-number/M5SF3KKRGLT5CPCKX7YEF5XYRN/events.json","paper":"https://pith.science/paper/M5SF3KKR"},"agent_actions":{"view_html":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN","download_json":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN.json","view_paper":"https://pith.science/paper/M5SF3KKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15182&json=true","fetch_graph":"https://pith.science/api/pith-number/M5SF3KKRGLT5CPCKX7YEF5XYRN/graph.json","fetch_events":"https://pith.science/api/pith-number/M5SF3KKRGLT5CPCKX7YEF5XYRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN/action/storage_attestation","attest_author":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN/action/author_attestation","sign_citation":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN/action/citation_signature","submit_replication":"https://pith.science/pith/M5SF3KKRGLT5CPCKX7YEF5XYRN/action/replication_record"}},"created_at":"2026-07-05T09:37:52.528454+00:00","updated_at":"2026-07-05T09:37:52.528454+00:00"}