{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EWGC6NNWQYKKULLWVGHQPCIFR2","short_pith_number":"pith:EWGC6NNW","schema_version":"1.0","canonical_sha256":"258c2f35b68614aa2d76a98f0789058e8c4e80bcb26d6d34ed906c01bd0e10f0","source":{"kind":"arxiv","id":"2310.00137","version":2},"attestation_state":"computed","paper":{"title":"On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Felix Dangel, Jonathan Wenger","submitted_at":"2023-09-29T20:51:24Z","abstract_excerpt":"The neural tangent kernel (NTK) has garnered significant attention as a theoretical framework for describing the behavior of large-scale neural networks. Kernel methods are theoretically well-understood and as a result enjoy algorithmic benefits, which can be demonstrated to hold in wide synthetic neural network architectures. These advantages include faster optimization, reliable uncertainty quantification and improved continual learning. However, current results quantifying the rate of convergence to the kernel regime suggest that exploiting these benefits requires architectures that are ord"},"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":"2310.00137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T20:51:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2549be46a4529c6ed31a31fe88bb9a4555bab80fbe1bf5e68a7c98f8f0156fef","abstract_canon_sha256":"07a1439b0dd83f1dfa8a8d623885ce2f3fb24884d0147cd558c55838421e1839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:22.609009Z","signature_b64":"oPGZRSDs8oOi4YoLg2NPovryt0TTiBv7xaMbJexEqMerDwNV8N9oM0bWFLrEQUazkvFxTsQ23BLFQT2OVwYoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258c2f35b68614aa2d76a98f0789058e8c4e80bcb26d6d34ed906c01bd0e10f0","last_reissued_at":"2026-07-05T08:24:22.608553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:22.608553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Felix Dangel, Jonathan Wenger","submitted_at":"2023-09-29T20:51:24Z","abstract_excerpt":"The neural tangent kernel (NTK) has garnered significant attention as a theoretical framework for describing the behavior of large-scale neural networks. Kernel methods are theoretically well-understood and as a result enjoy algorithmic benefits, which can be demonstrated to hold in wide synthetic neural network architectures. These advantages include faster optimization, reliable uncertainty quantification and improved continual learning. However, current results quantifying the rate of convergence to the kernel regime suggest that exploiting these benefits requires architectures that are ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00137","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/2310.00137/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":"2310.00137","created_at":"2026-07-05T08:24:22.608610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00137v2","created_at":"2026-07-05T08:24:22.608610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00137","created_at":"2026-07-05T08:24:22.608610+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWGC6NNWQYKK","created_at":"2026-07-05T08:24:22.608610+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWGC6NNWQYKKULLW","created_at":"2026-07-05T08:24:22.608610+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWGC6NNW","created_at":"2026-07-05T08:24:22.608610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20294","citing_title":"Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27052","citing_title":"Man, Machine, and Mathematics","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2","json":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2.json","graph_json":"https://pith.science/api/pith-number/EWGC6NNWQYKKULLWVGHQPCIFR2/graph.json","events_json":"https://pith.science/api/pith-number/EWGC6NNWQYKKULLWVGHQPCIFR2/events.json","paper":"https://pith.science/paper/EWGC6NNW"},"agent_actions":{"view_html":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2","download_json":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2.json","view_paper":"https://pith.science/paper/EWGC6NNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00137&json=true","fetch_graph":"https://pith.science/api/pith-number/EWGC6NNWQYKKULLWVGHQPCIFR2/graph.json","fetch_events":"https://pith.science/api/pith-number/EWGC6NNWQYKKULLWVGHQPCIFR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2/action/storage_attestation","attest_author":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2/action/author_attestation","sign_citation":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2/action/citation_signature","submit_replication":"https://pith.science/pith/EWGC6NNWQYKKULLWVGHQPCIFR2/action/replication_record"}},"created_at":"2026-07-05T08:24:22.608610+00:00","updated_at":"2026-07-05T08:24:22.608610+00:00"}