{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RFKCTJQD352GJHFUS5232RP7DC","short_pith_number":"pith:RFKCTJQD","schema_version":"1.0","canonical_sha256":"895429a603df74649cb49775bd45ff18b64316cc5fd601a7d9d9396580a2309a","source":{"kind":"arxiv","id":"1901.10232","version":1},"attestation_state":"computed","paper":{"title":"Multikernel activation functions: formulation and a case study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Donatella Firmani, Elena Nieddu, Paolo Merialdo, Simone Scardapane","submitted_at":"2019-01-29T11:41:27Z","abstract_excerpt":"The design of activation functions is a growing research area in the field of neural networks. In particular, instead of using fixed point-wise functions (e.g., the rectified linear unit), several authors have proposed ways of learning these functions directly from the data in a non-parametric fashion. In this paper we focus on the kernel activation function (KAF), a recently proposed framework wherein each function is modeled as a one-dimensional kernel model, whose weights are adapted through standard backpropagation-based optimization. One drawback of KAFs is the need to select a single ker"},"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":"1901.10232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T11:41:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e531786287c7b774c2ebe944234012c46411fda86e31ae9bce5225219226799d","abstract_canon_sha256":"4a62b327f3cc9e22c64607d2e19724abe9ec4b74354c5969c5f0ab267cf8388b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:15.787411Z","signature_b64":"CBMeABohg8Bkgux4S46xnlxMPmTnet2MItfcYkI4YAViMztVdfO6CtGoMq2cPGImckhthyZ4tqhzdR5hXu5TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"895429a603df74649cb49775bd45ff18b64316cc5fd601a7d9d9396580a2309a","last_reissued_at":"2026-05-17T23:55:15.786909Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:15.786909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multikernel activation functions: formulation and a case study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Donatella Firmani, Elena Nieddu, Paolo Merialdo, Simone Scardapane","submitted_at":"2019-01-29T11:41:27Z","abstract_excerpt":"The design of activation functions is a growing research area in the field of neural networks. In particular, instead of using fixed point-wise functions (e.g., the rectified linear unit), several authors have proposed ways of learning these functions directly from the data in a non-parametric fashion. In this paper we focus on the kernel activation function (KAF), a recently proposed framework wherein each function is modeled as a one-dimensional kernel model, whose weights are adapted through standard backpropagation-based optimization. One drawback of KAFs is the need to select a single ker"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10232","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":"1901.10232","created_at":"2026-05-17T23:55:15.786984+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10232v1","created_at":"2026-05-17T23:55:15.786984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10232","created_at":"2026-05-17T23:55:15.786984+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFKCTJQD352G","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFKCTJQD352GJHFU","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFKCTJQD","created_at":"2026-05-18T12:33:27.125529+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/RFKCTJQD352GJHFUS5232RP7DC","json":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC.json","graph_json":"https://pith.science/api/pith-number/RFKCTJQD352GJHFUS5232RP7DC/graph.json","events_json":"https://pith.science/api/pith-number/RFKCTJQD352GJHFUS5232RP7DC/events.json","paper":"https://pith.science/paper/RFKCTJQD"},"agent_actions":{"view_html":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC","download_json":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC.json","view_paper":"https://pith.science/paper/RFKCTJQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10232&json=true","fetch_graph":"https://pith.science/api/pith-number/RFKCTJQD352GJHFUS5232RP7DC/graph.json","fetch_events":"https://pith.science/api/pith-number/RFKCTJQD352GJHFUS5232RP7DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC/action/storage_attestation","attest_author":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC/action/author_attestation","sign_citation":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC/action/citation_signature","submit_replication":"https://pith.science/pith/RFKCTJQD352GJHFUS5232RP7DC/action/replication_record"}},"created_at":"2026-05-17T23:55:15.786984+00:00","updated_at":"2026-05-17T23:55:15.786984+00:00"}