{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VZHVMHRC3XDMFVI4SPQAHT5XMU","short_pith_number":"pith:VZHVMHRC","schema_version":"1.0","canonical_sha256":"ae4f561e22ddc6c2d51c93e003cfb7651ec198e55703c6ca74a7640e2c8b02ef","source":{"kind":"arxiv","id":"2109.09710","version":2},"attestation_state":"computed","paper":{"title":"Understanding neural networks with reproducing kernel Banach spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.FA"],"primary_cat":"stat.ML","authors_text":"Ernesto De Vito, Francesca Bartolucci, Lorenzo Rosasco, Stefano Vigogna","submitted_at":"2021-09-20T17:32:30Z","abstract_excerpt":"Characterizing the function spaces corresponding to neural networks can provide a way to understand their properties. In this paper we discuss how the theory of reproducing kernel Banach spaces can be used to tackle this challenge. In particular, we prove a representer theorem for a wide class of reproducing kernel Banach spaces that admit a suitable integral representation and include one hidden layer neural networks of possibly infinite width. Further, we show that, for a suitable class of ReLU activation functions, the norm in the corresponding reproducing kernel Banach space can be charact"},"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":"2109.09710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-20T17:32:30Z","cross_cats_sorted":["cs.LG","math.FA"],"title_canon_sha256":"ef1cf9070f0726cde17d7b761faef685e8d656cdf0ca6c1731036d232dcec8b9","abstract_canon_sha256":"a4e117cfcfe5e7a9b847229c4c496a325bc05a004ccb80b92f8ed193bd7ff336"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:34.487200Z","signature_b64":"9Uhddrm5i8P5xOirVBnOWrnbnvVOTofbQJgCEZ4BMlVIvEghDpbVJniXN7ZLdumGS1qq6DYutjIugG1S+YcrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4f561e22ddc6c2d51c93e003cfb7651ec198e55703c6ca74a7640e2c8b02ef","last_reissued_at":"2026-07-05T03:25:34.486786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:34.486786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding neural networks with reproducing kernel Banach spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.FA"],"primary_cat":"stat.ML","authors_text":"Ernesto De Vito, Francesca Bartolucci, Lorenzo Rosasco, Stefano Vigogna","submitted_at":"2021-09-20T17:32:30Z","abstract_excerpt":"Characterizing the function spaces corresponding to neural networks can provide a way to understand their properties. In this paper we discuss how the theory of reproducing kernel Banach spaces can be used to tackle this challenge. In particular, we prove a representer theorem for a wide class of reproducing kernel Banach spaces that admit a suitable integral representation and include one hidden layer neural networks of possibly infinite width. Further, we show that, for a suitable class of ReLU activation functions, the norm in the corresponding reproducing kernel Banach space can be charact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09710","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/2109.09710/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":"2109.09710","created_at":"2026-07-05T03:25:34.486838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09710v2","created_at":"2026-07-05T03:25:34.486838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09710","created_at":"2026-07-05T03:25:34.486838+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZHVMHRC3XDM","created_at":"2026-07-05T03:25:34.486838+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZHVMHRC3XDMFVI4","created_at":"2026-07-05T03:25:34.486838+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZHVMHRC","created_at":"2026-07-05T03:25:34.486838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04549","citing_title":"Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU","json":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU.json","graph_json":"https://pith.science/api/pith-number/VZHVMHRC3XDMFVI4SPQAHT5XMU/graph.json","events_json":"https://pith.science/api/pith-number/VZHVMHRC3XDMFVI4SPQAHT5XMU/events.json","paper":"https://pith.science/paper/VZHVMHRC"},"agent_actions":{"view_html":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU","download_json":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU.json","view_paper":"https://pith.science/paper/VZHVMHRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09710&json=true","fetch_graph":"https://pith.science/api/pith-number/VZHVMHRC3XDMFVI4SPQAHT5XMU/graph.json","fetch_events":"https://pith.science/api/pith-number/VZHVMHRC3XDMFVI4SPQAHT5XMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU/action/storage_attestation","attest_author":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU/action/author_attestation","sign_citation":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU/action/citation_signature","submit_replication":"https://pith.science/pith/VZHVMHRC3XDMFVI4SPQAHT5XMU/action/replication_record"}},"created_at":"2026-07-05T03:25:34.486838+00:00","updated_at":"2026-07-05T03:25:34.486838+00:00"}