{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JQTY6CBTNN24J5KP3UK4BTE6AR","short_pith_number":"pith:JQTY6CBT","schema_version":"1.0","canonical_sha256":"4c278f08336b75c4f54fdd15c0cc9e044cc44e69bc2793c4da27ac94a1a36a42","source":{"kind":"arxiv","id":"1903.08131","version":1},"attestation_state":"computed","paper":{"title":"Kernel-based Translations of Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Corinne Jones, Vincent Roulet, Zaid Harchaoui","submitted_at":"2019-03-19T17:41:48Z","abstract_excerpt":"Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods. We provide a systematic translation of Convolutional Neural Networks (ConvNets) into their kernel-based counterparts, Convolutional Kernel Networks (CKNs), and demonstrate that this perception is unfounded both formally and empirically. We show that, given a Convolutional Neural Network, we can design a corresponding Convolutional Kernel Network, easily trainable using a new stochastic gradient algorithm based on an accurate gradient computation, tha"},"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":"1903.08131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-19T17:41:48Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"b4462c563ae580fa5f86bc888d278fa57c4fc3402ed6b77179488d6d83ee9dcf","abstract_canon_sha256":"89ba248ded7581771cf428bfc4d02c44d476d23b2a46d52a6fdb287eb07a3fea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:52.873091Z","signature_b64":"4V4/HzsXfht4dmYHPDnSISbhP7EQSITiI/STutxZl+nV1uPaOjWlkEuyMeThqkCCoQmS+AzWZItw5oTCzOypBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c278f08336b75c4f54fdd15c0cc9e044cc44e69bc2793c4da27ac94a1a36a42","last_reissued_at":"2026-05-17T23:50:52.872492Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:52.872492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel-based Translations of Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Corinne Jones, Vincent Roulet, Zaid Harchaoui","submitted_at":"2019-03-19T17:41:48Z","abstract_excerpt":"Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods. We provide a systematic translation of Convolutional Neural Networks (ConvNets) into their kernel-based counterparts, Convolutional Kernel Networks (CKNs), and demonstrate that this perception is unfounded both formally and empirically. We show that, given a Convolutional Neural Network, we can design a corresponding Convolutional Kernel Network, easily trainable using a new stochastic gradient algorithm based on an accurate gradient computation, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08131","kind":"arxiv","version":1},"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":"1903.08131","created_at":"2026-05-17T23:50:52.872570+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08131v1","created_at":"2026-05-17T23:50:52.872570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08131","created_at":"2026-05-17T23:50:52.872570+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQTY6CBTNN24","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQTY6CBTNN24J5KP","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQTY6CBT","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02603","citing_title":"Additive function approximation in the brain","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR","json":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR.json","graph_json":"https://pith.science/api/pith-number/JQTY6CBTNN24J5KP3UK4BTE6AR/graph.json","events_json":"https://pith.science/api/pith-number/JQTY6CBTNN24J5KP3UK4BTE6AR/events.json","paper":"https://pith.science/paper/JQTY6CBT"},"agent_actions":{"view_html":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR","download_json":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR.json","view_paper":"https://pith.science/paper/JQTY6CBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08131&json=true","fetch_graph":"https://pith.science/api/pith-number/JQTY6CBTNN24J5KP3UK4BTE6AR/graph.json","fetch_events":"https://pith.science/api/pith-number/JQTY6CBTNN24J5KP3UK4BTE6AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR/action/storage_attestation","attest_author":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR/action/author_attestation","sign_citation":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR/action/citation_signature","submit_replication":"https://pith.science/pith/JQTY6CBTNN24J5KP3UK4BTE6AR/action/replication_record"}},"created_at":"2026-05-17T23:50:52.872570+00:00","updated_at":"2026-05-17T23:50:52.872570+00:00"}