{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GWZ4Z3CKIXDXRNJISILADVHYLU","short_pith_number":"pith:GWZ4Z3CK","schema_version":"1.0","canonical_sha256":"35b3ccec4a45c778b528921601d4f85d1bd60632f095a29a8d6de2323ffebee1","source":{"kind":"arxiv","id":"1807.07868","version":2},"attestation_state":"computed","paper":{"title":"The Deep Kernelized Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Filippo M. Bianchi, Lorenzo Livi, Michael Kampffmeyer, Robert Jenssen, Sigurd L{\\o}kse","submitted_at":"2018-07-19T14:47:32Z","abstract_excerpt":"Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel machines have experienced great success by operating via inner-products in a theoretically well-defined reproducing kernel Hilbert space, hence capturing topological properties of input data. In this paper, we enhance the autoencoder's ability to learn effective data representations by aligning inner products between codes with respect to a kernel matrix. By doi"},"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":"1807.07868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T14:47:32Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"09b67b06d343edce59f07431291447865b6e38dfce981401edae8e4f0ba07ba0","abstract_canon_sha256":"b538e2c55287548fa05d5ac92c1c049ed21f8ee6bff5276da05872cfeef49df1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:09.664835Z","signature_b64":"4oWSxWzDPolr3NCTGi60htQtG5enpBwTcp6gq/hPuRKHGY/VLt8MyNoh1AJFD426YXbA1ac95cmDKtCBHtjUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b3ccec4a45c778b528921601d4f85d1bd60632f095a29a8d6de2323ffebee1","last_reissued_at":"2026-05-18T00:10:09.664168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:09.664168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Deep Kernelized Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Filippo M. Bianchi, Lorenzo Livi, Michael Kampffmeyer, Robert Jenssen, Sigurd L{\\o}kse","submitted_at":"2018-07-19T14:47:32Z","abstract_excerpt":"Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel machines have experienced great success by operating via inner-products in a theoretically well-defined reproducing kernel Hilbert space, hence capturing topological properties of input data. In this paper, we enhance the autoencoder's ability to learn effective data representations by aligning inner products between codes with respect to a kernel matrix. By doi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07868","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":"1807.07868","created_at":"2026-05-18T00:10:09.664268+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.07868v2","created_at":"2026-05-18T00:10:09.664268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07868","created_at":"2026-05-18T00:10:09.664268+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWZ4Z3CKIXDX","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWZ4Z3CKIXDXRNJI","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWZ4Z3CK","created_at":"2026-05-18T12:32:25.280505+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/GWZ4Z3CKIXDXRNJISILADVHYLU","json":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU.json","graph_json":"https://pith.science/api/pith-number/GWZ4Z3CKIXDXRNJISILADVHYLU/graph.json","events_json":"https://pith.science/api/pith-number/GWZ4Z3CKIXDXRNJISILADVHYLU/events.json","paper":"https://pith.science/paper/GWZ4Z3CK"},"agent_actions":{"view_html":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU","download_json":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU.json","view_paper":"https://pith.science/paper/GWZ4Z3CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.07868&json=true","fetch_graph":"https://pith.science/api/pith-number/GWZ4Z3CKIXDXRNJISILADVHYLU/graph.json","fetch_events":"https://pith.science/api/pith-number/GWZ4Z3CKIXDXRNJISILADVHYLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU/action/storage_attestation","attest_author":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU/action/author_attestation","sign_citation":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU/action/citation_signature","submit_replication":"https://pith.science/pith/GWZ4Z3CKIXDXRNJISILADVHYLU/action/replication_record"}},"created_at":"2026-05-18T00:10:09.664268+00:00","updated_at":"2026-05-18T00:10:09.664268+00:00"}