{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5O642CCC2MVCXSUPXZOPDXJYFB","short_pith_number":"pith:5O642CCC","schema_version":"1.0","canonical_sha256":"ebbdcd0842d32a2bca8fbe5cf1dd38286f99ca387fd6ecfb91f174a93f72c11c","source":{"kind":"arxiv","id":"2210.00935","version":4},"attestation_state":"computed","paper":{"title":"Analysis of (sub-)Riemannian PDE-G-CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","math.DG"],"primary_cat":"cs.LG","authors_text":"Bart M. N. Smets, Daan L. J. Bon, Gautam Pai, Gijs Bellaard, Remco Duits","submitted_at":"2022-10-03T13:47:47Z","abstract_excerpt":"Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalises G-CNNs. PDE-G-CNNs have the core advantages that they simultaneously 1) reduce network complexity, 2) increase classification performance, and 3) provide geometric interpretability. Their implementations primarily consist of linear and morphologi"},"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":"2210.00935","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T13:47:47Z","cross_cats_sorted":["cs.CV","math.DG"],"title_canon_sha256":"9b333ca00bfe167608f65c38600cc6b397f4910da3e31b690569dc2a706b8825","abstract_canon_sha256":"877f274e0a1b05dea64a555cf5cfaed6e1eaa9d9ba066f3a3732f626fc4b949b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:13.009289Z","signature_b64":"grh/9reL6oJXXqpQV+1NkWg1pvDjUZJ2oyScXPzgCK/ighLedlYXo5lWpgTyf7Mu3ViDlj2zi7UI46d4N5q0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebbdcd0842d32a2bca8fbe5cf1dd38286f99ca387fd6ecfb91f174a93f72c11c","last_reissued_at":"2026-07-05T05:57:13.008866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:13.008866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of (sub-)Riemannian PDE-G-CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","math.DG"],"primary_cat":"cs.LG","authors_text":"Bart M. N. Smets, Daan L. J. Bon, Gautam Pai, Gijs Bellaard, Remco Duits","submitted_at":"2022-10-03T13:47:47Z","abstract_excerpt":"Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalises G-CNNs. PDE-G-CNNs have the core advantages that they simultaneously 1) reduce network complexity, 2) increase classification performance, and 3) provide geometric interpretability. Their implementations primarily consist of linear and morphologi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00935","kind":"arxiv","version":4},"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/2210.00935/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":"2210.00935","created_at":"2026-07-05T05:57:13.008923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00935v4","created_at":"2026-07-05T05:57:13.008923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00935","created_at":"2026-07-05T05:57:13.008923+00:00"},{"alias_kind":"pith_short_12","alias_value":"5O642CCC2MVC","created_at":"2026-07-05T05:57:13.008923+00:00"},{"alias_kind":"pith_short_16","alias_value":"5O642CCC2MVCXSUP","created_at":"2026-07-05T05:57:13.008923+00:00"},{"alias_kind":"pith_short_8","alias_value":"5O642CCC","created_at":"2026-07-05T05:57:13.008923+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/5O642CCC2MVCXSUPXZOPDXJYFB","json":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB.json","graph_json":"https://pith.science/api/pith-number/5O642CCC2MVCXSUPXZOPDXJYFB/graph.json","events_json":"https://pith.science/api/pith-number/5O642CCC2MVCXSUPXZOPDXJYFB/events.json","paper":"https://pith.science/paper/5O642CCC"},"agent_actions":{"view_html":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB","download_json":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB.json","view_paper":"https://pith.science/paper/5O642CCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00935&json=true","fetch_graph":"https://pith.science/api/pith-number/5O642CCC2MVCXSUPXZOPDXJYFB/graph.json","fetch_events":"https://pith.science/api/pith-number/5O642CCC2MVCXSUPXZOPDXJYFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB/action/storage_attestation","attest_author":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB/action/author_attestation","sign_citation":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB/action/citation_signature","submit_replication":"https://pith.science/pith/5O642CCC2MVCXSUPXZOPDXJYFB/action/replication_record"}},"created_at":"2026-07-05T05:57:13.008923+00:00","updated_at":"2026-07-05T05:57:13.008923+00:00"}