{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C3UDQT22JNEC2Q3FMZPR3WBJKH","short_pith_number":"pith:C3UDQT22","schema_version":"1.0","canonical_sha256":"16e8384f5a4b482d4365665f1dd82951c0cec70fabc19d5f77fbbc81aa55fefb","source":{"kind":"arxiv","id":"2505.20553","version":2},"attestation_state":"computed","paper":{"title":"A ZeNN architecture to avoid the Gaussian trap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Gon\\c{c}alo Oliveira, Jo\\~ao L. Costa, Jos\\'e Mour\\~ao, Lu\\'is Carvalho","submitted_at":"2025-05-26T22:26:55Z","abstract_excerpt":"We propose a new simple architecture, Zeta Neural Networks (ZeNNs), in order to overcome several shortcomings of standard multi-layer perceptrons (MLPs). Namely, in the large width limit, MLPs are non-parametric, they do not have a well-defined pointwise limit, they lose non-Gaussian attributes and become unable to perform feature learning; moreover, finite width MLPs perform poorly in learning high frequencies. The new ZeNN architecture is inspired by three simple principles from harmonic analysis:\n  i) Enumerate the perceptons and introduce a non-learnable weight to enforce convergence;\n  ii"},"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":"2505.20553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T22:26:55Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"256319493f165be1a260965541c94dbdea7deece6a6fca31afd111dce51737e8","abstract_canon_sha256":"d4ba6a6bb70850bd1369cb056670e8168c30debd348ed5303b303596ae773b95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:58.378198Z","signature_b64":"BSbNytOQ6ntYFDcTwQD9j888WWZESivA80HIX8wVJU5CcrV8u4BTZDAV3zYHGT4QrjwAsUYQS5i9b1LFSqf0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e8384f5a4b482d4365665f1dd82951c0cec70fabc19d5f77fbbc81aa55fefb","last_reissued_at":"2026-07-05T11:45:58.377576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:58.377576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A ZeNN architecture to avoid the Gaussian trap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Gon\\c{c}alo Oliveira, Jo\\~ao L. Costa, Jos\\'e Mour\\~ao, Lu\\'is Carvalho","submitted_at":"2025-05-26T22:26:55Z","abstract_excerpt":"We propose a new simple architecture, Zeta Neural Networks (ZeNNs), in order to overcome several shortcomings of standard multi-layer perceptrons (MLPs). Namely, in the large width limit, MLPs are non-parametric, they do not have a well-defined pointwise limit, they lose non-Gaussian attributes and become unable to perform feature learning; moreover, finite width MLPs perform poorly in learning high frequencies. The new ZeNN architecture is inspired by three simple principles from harmonic analysis:\n  i) Enumerate the perceptons and introduce a non-learnable weight to enforce convergence;\n  ii"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20553","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20553/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":"2505.20553","created_at":"2026-07-05T11:45:58.377641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20553v2","created_at":"2026-07-05T11:45:58.377641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20553","created_at":"2026-07-05T11:45:58.377641+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3UDQT22JNEC","created_at":"2026-07-05T11:45:58.377641+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3UDQT22JNEC2Q3F","created_at":"2026-07-05T11:45:58.377641+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3UDQT22","created_at":"2026-07-05T11:45:58.377641+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/C3UDQT22JNEC2Q3FMZPR3WBJKH","json":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH.json","graph_json":"https://pith.science/api/pith-number/C3UDQT22JNEC2Q3FMZPR3WBJKH/graph.json","events_json":"https://pith.science/api/pith-number/C3UDQT22JNEC2Q3FMZPR3WBJKH/events.json","paper":"https://pith.science/paper/C3UDQT22"},"agent_actions":{"view_html":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH","download_json":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH.json","view_paper":"https://pith.science/paper/C3UDQT22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20553&json=true","fetch_graph":"https://pith.science/api/pith-number/C3UDQT22JNEC2Q3FMZPR3WBJKH/graph.json","fetch_events":"https://pith.science/api/pith-number/C3UDQT22JNEC2Q3FMZPR3WBJKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH/action/storage_attestation","attest_author":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH/action/author_attestation","sign_citation":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH/action/citation_signature","submit_replication":"https://pith.science/pith/C3UDQT22JNEC2Q3FMZPR3WBJKH/action/replication_record"}},"created_at":"2026-07-05T11:45:58.377641+00:00","updated_at":"2026-07-05T11:45:58.377641+00:00"}