{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJV7OBCMSRQTG4AFIPS34BJGJG","short_pith_number":"pith:XJV7OBCM","schema_version":"1.0","canonical_sha256":"ba6bf7044c946133700543e5be05264994a40c9f492c8ce19c9dd7633fb34131","source":{"kind":"arxiv","id":"2410.05626","version":1},"attestation_state":"computed","paper":{"title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guhan Chen, Qian Lin, Yicheng Li","submitted_at":"2024-10-08T02:22:50Z","abstract_excerpt":"This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to infinity, the neural network with random initialization converges to a Gaussian process $f^{\\mathrm{GP}}$, which takes values in $L^{2}(\\mathcal{X})$, where $\\mathcal{X}$ is the domain of the data. In contrast, to adopt the traditional theory of kernel regression, most recent works introduced a special mirrored architecture and a mirrored (random) initialization"},"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":"2410.05626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-08T02:22:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"422518ca968424462f782d6fdbcc264520c83d128d7a75a0e1dda45b707f0dfc","abstract_canon_sha256":"18a7d9287625a4a9177e8345ffe674aa3fcaa60b2d6a615c7270402e2382e4ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:22.211806Z","signature_b64":"pi19GqX6D649XHE2ZsZbCAsQaLPFJinS0zhJhSTmlH8HlpytFbsL7gO8vcXsBRt/k/nlojR/s49Z77lxA4OwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba6bf7044c946133700543e5be05264994a40c9f492c8ce19c9dd7633fb34131","last_reissued_at":"2026-07-05T09:17:22.211211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:22.211211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guhan Chen, Qian Lin, Yicheng Li","submitted_at":"2024-10-08T02:22:50Z","abstract_excerpt":"This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to infinity, the neural network with random initialization converges to a Gaussian process $f^{\\mathrm{GP}}$, which takes values in $L^{2}(\\mathcal{X})$, where $\\mathcal{X}$ is the domain of the data. In contrast, to adopt the traditional theory of kernel regression, most recent works introduced a special mirrored architecture and a mirrored (random) initialization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05626","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/2410.05626/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":"2410.05626","created_at":"2026-07-05T09:17:22.211274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05626v1","created_at":"2026-07-05T09:17:22.211274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05626","created_at":"2026-07-05T09:17:22.211274+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJV7OBCMSRQT","created_at":"2026-07-05T09:17:22.211274+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJV7OBCMSRQTG4AF","created_at":"2026-07-05T09:17:22.211274+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJV7OBCM","created_at":"2026-07-05T09:17:22.211274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18756","citing_title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG","json":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG.json","graph_json":"https://pith.science/api/pith-number/XJV7OBCMSRQTG4AFIPS34BJGJG/graph.json","events_json":"https://pith.science/api/pith-number/XJV7OBCMSRQTG4AFIPS34BJGJG/events.json","paper":"https://pith.science/paper/XJV7OBCM"},"agent_actions":{"view_html":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG","download_json":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG.json","view_paper":"https://pith.science/paper/XJV7OBCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05626&json=true","fetch_graph":"https://pith.science/api/pith-number/XJV7OBCMSRQTG4AFIPS34BJGJG/graph.json","fetch_events":"https://pith.science/api/pith-number/XJV7OBCMSRQTG4AFIPS34BJGJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG/action/storage_attestation","attest_author":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG/action/author_attestation","sign_citation":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG/action/citation_signature","submit_replication":"https://pith.science/pith/XJV7OBCMSRQTG4AFIPS34BJGJG/action/replication_record"}},"created_at":"2026-07-05T09:17:22.211274+00:00","updated_at":"2026-07-05T09:17:22.211274+00:00"}