{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YV7RBGUQXE2AQ5CS72GQABO63G","short_pith_number":"pith:YV7RBGUQ","schema_version":"1.0","canonical_sha256":"c57f109a90b934087452fe8d0005ded988e877897f95b475a63d56513cee5a89","source":{"kind":"arxiv","id":"2501.00420","version":1},"attestation_state":"computed","paper":{"title":"KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangchen Yu, Ruilizhen Hu, Wenye Li, Yidong Lin, Yuqi Ma, Zhenghao Huang","submitted_at":"2024-12-31T12:49:03Z","abstract_excerpt":"The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demons"},"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":"2501.00420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T12:49:03Z","cross_cats_sorted":[],"title_canon_sha256":"ebd2a51ebfc1b2bb65a0ec2acc18c06ef330b9c86e704511fc92e385ca27b6c5","abstract_canon_sha256":"4748dbf32023e85da670231248f831ba713729456feeff13344d2c7dcfa90b6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:05.658796Z","signature_b64":"wGCS0nEfK4o8/FiNs+7UPVsfAzy3WKeK70Gazhb8EUYFPzrI6QHYUfRZ5tsTLzsqRkTNp9aYfdTEPp4fBaFBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c57f109a90b934087452fe8d0005ded988e877897f95b475a63d56513cee5a89","last_reissued_at":"2026-07-05T09:56:05.658337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:05.658337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangchen Yu, Ruilizhen Hu, Wenye Li, Yidong Lin, Yuqi Ma, Zhenghao Huang","submitted_at":"2024-12-31T12:49:03Z","abstract_excerpt":"The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00420","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.00420/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":"2501.00420","created_at":"2026-07-05T09:56:05.658400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00420v1","created_at":"2026-07-05T09:56:05.658400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00420","created_at":"2026-07-05T09:56:05.658400+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV7RBGUQXE2A","created_at":"2026-07-05T09:56:05.658400+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV7RBGUQXE2AQ5CS","created_at":"2026-07-05T09:56:05.658400+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV7RBGUQ","created_at":"2026-07-05T09:56:05.658400+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/YV7RBGUQXE2AQ5CS72GQABO63G","json":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G.json","graph_json":"https://pith.science/api/pith-number/YV7RBGUQXE2AQ5CS72GQABO63G/graph.json","events_json":"https://pith.science/api/pith-number/YV7RBGUQXE2AQ5CS72GQABO63G/events.json","paper":"https://pith.science/paper/YV7RBGUQ"},"agent_actions":{"view_html":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G","download_json":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G.json","view_paper":"https://pith.science/paper/YV7RBGUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00420&json=true","fetch_graph":"https://pith.science/api/pith-number/YV7RBGUQXE2AQ5CS72GQABO63G/graph.json","fetch_events":"https://pith.science/api/pith-number/YV7RBGUQXE2AQ5CS72GQABO63G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G/action/storage_attestation","attest_author":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G/action/author_attestation","sign_citation":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G/action/citation_signature","submit_replication":"https://pith.science/pith/YV7RBGUQXE2AQ5CS72GQABO63G/action/replication_record"}},"created_at":"2026-07-05T09:56:05.658400+00:00","updated_at":"2026-07-05T09:56:05.658400+00:00"}