{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FP3SXFMREDGFAOC2TTTOPMNRXL","short_pith_number":"pith:FP3SXFMR","schema_version":"1.0","canonical_sha256":"2bf72b959120cc50385a9ce6e7b1b1baedc557f4834a11955e3bc1d789255fb5","source":{"kind":"arxiv","id":"2501.03697","version":1},"attestation_state":"computed","paper":{"title":"Deep Networks are Reproducing Kernel Chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Brune, Len Spek, Tjeerd Jan Heeringa","submitted_at":"2025-01-07T11:01:24Z","abstract_excerpt":"Identifying an appropriate function space for deep neural networks remains a key open question. While shallow neural networks are naturally associated with Reproducing Kernel Banach Spaces (RKBS), deep networks present unique challenges. In this work, we extend RKBS to chain RKBS (cRKBS), a new framework that composes kernels rather than functions, preserving the desirable properties of RKBS. We prove that any deep neural network function is a neural cRKBS function, and conversely, any neural cRKBS function defined on a finite dataset corresponds to a deep neural network. This approach provide"},"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":"2501.03697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T11:01:24Z","cross_cats_sorted":["math.FA","stat.ML"],"title_canon_sha256":"b54c3d1b2891cb79d352b5a9908424203e695ceb20e0371a713fa52bd82e27e2","abstract_canon_sha256":"10cb34f2bd1c29012f2e439a11a010eb276692c5da6a3c621f9c7895c4db1738"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:58.600631Z","signature_b64":"+7s4IqDD9EzSTZWY29rVcAHUqUdo3yCZ5qi9bCnBTSEZDQaPctHyDUTkCji7HAPAgFWIdv2f7Lhnt+GAWN7GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf72b959120cc50385a9ce6e7b1b1baedc557f4834a11955e3bc1d789255fb5","last_reissued_at":"2026-07-05T09:57:58.600153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:58.600153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Networks are Reproducing Kernel Chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Brune, Len Spek, Tjeerd Jan Heeringa","submitted_at":"2025-01-07T11:01:24Z","abstract_excerpt":"Identifying an appropriate function space for deep neural networks remains a key open question. While shallow neural networks are naturally associated with Reproducing Kernel Banach Spaces (RKBS), deep networks present unique challenges. In this work, we extend RKBS to chain RKBS (cRKBS), a new framework that composes kernels rather than functions, preserving the desirable properties of RKBS. We prove that any deep neural network function is a neural cRKBS function, and conversely, any neural cRKBS function defined on a finite dataset corresponds to a deep neural network. This approach provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03697","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/2501.03697/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":"2501.03697","created_at":"2026-07-05T09:57:58.600216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03697v1","created_at":"2026-07-05T09:57:58.600216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03697","created_at":"2026-07-05T09:57:58.600216+00:00"},{"alias_kind":"pith_short_12","alias_value":"FP3SXFMREDGF","created_at":"2026-07-05T09:57:58.600216+00:00"},{"alias_kind":"pith_short_16","alias_value":"FP3SXFMREDGFAOC2","created_at":"2026-07-05T09:57:58.600216+00:00"},{"alias_kind":"pith_short_8","alias_value":"FP3SXFMR","created_at":"2026-07-05T09:57:58.600216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14954","citing_title":"Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19458","citing_title":"Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL","json":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL.json","graph_json":"https://pith.science/api/pith-number/FP3SXFMREDGFAOC2TTTOPMNRXL/graph.json","events_json":"https://pith.science/api/pith-number/FP3SXFMREDGFAOC2TTTOPMNRXL/events.json","paper":"https://pith.science/paper/FP3SXFMR"},"agent_actions":{"view_html":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL","download_json":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL.json","view_paper":"https://pith.science/paper/FP3SXFMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03697&json=true","fetch_graph":"https://pith.science/api/pith-number/FP3SXFMREDGFAOC2TTTOPMNRXL/graph.json","fetch_events":"https://pith.science/api/pith-number/FP3SXFMREDGFAOC2TTTOPMNRXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL/action/storage_attestation","attest_author":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL/action/author_attestation","sign_citation":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL/action/citation_signature","submit_replication":"https://pith.science/pith/FP3SXFMREDGFAOC2TTTOPMNRXL/action/replication_record"}},"created_at":"2026-07-05T09:57:58.600216+00:00","updated_at":"2026-07-05T09:57:58.600216+00:00"}