{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCNWMNUP52ZV2EQAEDQDTU3QKZ","short_pith_number":"pith:GCNWMNUP","schema_version":"1.0","canonical_sha256":"309b66368feeb35d120020e039d370564431a953964992b4baf57a26af8ead34","source":{"kind":"arxiv","id":"2503.06112","version":1},"attestation_state":"computed","paper":{"title":"AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anh Tran, Hoang-Thang Ta","submitted_at":"2025-03-08T07:38:51Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce "},"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":"2503.06112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-08T07:38:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e8644431ddbff310b8647183513c97755487887f6f19a5cbfceb7d552c180bc7","abstract_canon_sha256":"c2c5b57f0d35e3c23d9cd56ecf8e2c17586e111f05f020ed4f37e4b225a76aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:54.381781Z","signature_b64":"1bDV7dvGdL6vVQaVOO7OKfORadd0dXd6k5a2KpjjwT3HiaGFNV9fkwzncWjS4peXU6uU7q8hizNeek+DJ1oJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309b66368feeb35d120020e039d370564431a953964992b4baf57a26af8ead34","last_reissued_at":"2026-07-05T10:26:54.381387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:54.381387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anh Tran, Hoang-Thang Ta","submitted_at":"2025-03-08T07:38:51Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06112","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/2503.06112/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":"2503.06112","created_at":"2026-07-05T10:26:54.381446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06112v1","created_at":"2026-07-05T10:26:54.381446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06112","created_at":"2026-07-05T10:26:54.381446+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCNWMNUP52ZV","created_at":"2026-07-05T10:26:54.381446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCNWMNUP52ZV2EQA","created_at":"2026-07-05T10:26:54.381446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCNWMNUP","created_at":"2026-07-05T10:26:54.381446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12580","citing_title":"ChemKANs for Combustion Chemistry Modeling and Acceleration","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ","json":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ.json","graph_json":"https://pith.science/api/pith-number/GCNWMNUP52ZV2EQAEDQDTU3QKZ/graph.json","events_json":"https://pith.science/api/pith-number/GCNWMNUP52ZV2EQAEDQDTU3QKZ/events.json","paper":"https://pith.science/paper/GCNWMNUP"},"agent_actions":{"view_html":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ","download_json":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ.json","view_paper":"https://pith.science/paper/GCNWMNUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06112&json=true","fetch_graph":"https://pith.science/api/pith-number/GCNWMNUP52ZV2EQAEDQDTU3QKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GCNWMNUP52ZV2EQAEDQDTU3QKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ/action/storage_attestation","attest_author":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ/action/author_attestation","sign_citation":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ/action/citation_signature","submit_replication":"https://pith.science/pith/GCNWMNUP52ZV2EQAEDQDTU3QKZ/action/replication_record"}},"created_at":"2026-07-05T10:26:54.381446+00:00","updated_at":"2026-07-05T10:26:54.381446+00:00"}