{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CWOWQN5JTMMWT2E4YRXSIEN5G6","short_pith_number":"pith:CWOWQN5J","schema_version":"1.0","canonical_sha256":"159d6837a99b1969e89cc46f2411bd378be727406d797a6a529dc231fa95d395","source":{"kind":"arxiv","id":"2307.16695","version":2},"attestation_state":"computed","paper":{"title":"A theory of data variability in Neural Network Bayesian inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"David Dahmen, Javed Lindner, Michael Kr\\\"amer, Moritz Helias","submitted_at":"2023-07-31T14:11:32Z","abstract_excerpt":"Bayesian inference and kernel methods are well established in machine learning. The neural network Gaussian process in particular provides a concept to investigate neural networks in the limit of infinitely wide hidden layers by using kernel and inference methods. Here we build upon this limit and provide a field-theoretic formalism which covers the generalization properties of infinitely wide networks. We systematically compute generalization properties of linear, non-linear, and deep non-linear networks for kernel matrices with heterogeneous entries. In contrast to currently employed spectra"},"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":"2307.16695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2023-07-31T14:11:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"077df62dcdb0493064f94e3c1644f8d7ea1ef754735607ee0836d739c827b19e","abstract_canon_sha256":"8dc302358a609dcc4eeccdc1be0bbb6b86388ef8b51f3055c3af87ac81522f6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:49.264817Z","signature_b64":"DlXNCNS2d9DSsureH5WPZDMfpSt186OJHtxi1YT4qOaXOcRR2aQKQfRsvRuKm70+ZuMgROBXoLPXlEzuvmEfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159d6837a99b1969e89cc46f2411bd378be727406d797a6a529dc231fa95d395","last_reissued_at":"2026-07-05T07:10:49.264348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:49.264348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A theory of data variability in Neural Network Bayesian inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"David Dahmen, Javed Lindner, Michael Kr\\\"amer, Moritz Helias","submitted_at":"2023-07-31T14:11:32Z","abstract_excerpt":"Bayesian inference and kernel methods are well established in machine learning. The neural network Gaussian process in particular provides a concept to investigate neural networks in the limit of infinitely wide hidden layers by using kernel and inference methods. Here we build upon this limit and provide a field-theoretic formalism which covers the generalization properties of infinitely wide networks. We systematically compute generalization properties of linear, non-linear, and deep non-linear networks for kernel matrices with heterogeneous entries. In contrast to currently employed spectra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16695","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/2307.16695/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":"2307.16695","created_at":"2026-07-05T07:10:49.264407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16695v2","created_at":"2026-07-05T07:10:49.264407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16695","created_at":"2026-07-05T07:10:49.264407+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWOWQN5JTMMW","created_at":"2026-07-05T07:10:49.264407+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWOWQN5JTMMWT2E4","created_at":"2026-07-05T07:10:49.264407+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWOWQN5J","created_at":"2026-07-05T07:10:49.264407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.01976","citing_title":"A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6","json":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6.json","graph_json":"https://pith.science/api/pith-number/CWOWQN5JTMMWT2E4YRXSIEN5G6/graph.json","events_json":"https://pith.science/api/pith-number/CWOWQN5JTMMWT2E4YRXSIEN5G6/events.json","paper":"https://pith.science/paper/CWOWQN5J"},"agent_actions":{"view_html":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6","download_json":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6.json","view_paper":"https://pith.science/paper/CWOWQN5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16695&json=true","fetch_graph":"https://pith.science/api/pith-number/CWOWQN5JTMMWT2E4YRXSIEN5G6/graph.json","fetch_events":"https://pith.science/api/pith-number/CWOWQN5JTMMWT2E4YRXSIEN5G6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6/action/storage_attestation","attest_author":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6/action/author_attestation","sign_citation":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6/action/citation_signature","submit_replication":"https://pith.science/pith/CWOWQN5JTMMWT2E4YRXSIEN5G6/action/replication_record"}},"created_at":"2026-07-05T07:10:49.264407+00:00","updated_at":"2026-07-05T07:10:49.264407+00:00"}