{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYC3LECPDTCYJNJKIL455DFBYW","short_pith_number":"pith:MYC3LECP","schema_version":"1.0","canonical_sha256":"6605b5904f1cc584b52a42f9de8ca1c5ae24ce4b6691d11daf11996ffbeae261","source":{"kind":"arxiv","id":"2412.18756","version":1},"attestation_state":"computed","paper":{"title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Haobo Zhang, Jianfa Lai, Jun S. Liu, Qian Lin, Yicheng Li","submitted_at":"2024-12-25T03:03:58Z","abstract_excerpt":"A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamics. We propose a new paradigm for studying feature learning and the resulting benefits in generalizability. After reviewing the neural tangent kernel (NTK) theory and recent results in kernel regression, which address the generalization issue of sufficiently wide neural networks, we examine limitations and implications of the fixed kernel theory (as the NTK theory) and review recent theoretical advancements in feature"},"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":"2412.18756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T03:03:58Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"4621abdddfe1f8b7ce0de10a3fb7764f61e4c6decdc815e0871070ea38309a1f","abstract_canon_sha256":"096b70f61a3276198746a98df503a93e1bd5a3883fe9717797754dac1b16cf38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:10.218747Z","signature_b64":"Q+f80gLnD8lhmPYx60BIMPJ1VJlpuMdnETD4uE6TeeaZg8djN0+I9uJzxxlNDrJnZ9IWoi33FlOf2k977h+BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6605b5904f1cc584b52a42f9de8ca1c5ae24ce4b6691d11daf11996ffbeae261","last_reissued_at":"2026-07-05T09:54:10.218374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:10.218374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Haobo Zhang, Jianfa Lai, Jun S. Liu, Qian Lin, Yicheng Li","submitted_at":"2024-12-25T03:03:58Z","abstract_excerpt":"A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamics. We propose a new paradigm for studying feature learning and the resulting benefits in generalizability. After reviewing the neural tangent kernel (NTK) theory and recent results in kernel regression, which address the generalization issue of sufficiently wide neural networks, we examine limitations and implications of the fixed kernel theory (as the NTK theory) and review recent theoretical advancements in feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18756","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/2412.18756/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":"2412.18756","created_at":"2026-07-05T09:54:10.218429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18756v1","created_at":"2026-07-05T09:54:10.218429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18756","created_at":"2026-07-05T09:54:10.218429+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYC3LECPDTCY","created_at":"2026-07-05T09:54:10.218429+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYC3LECPDTCYJNJK","created_at":"2026-07-05T09:54:10.218429+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYC3LECP","created_at":"2026-07-05T09:54:10.218429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2509.20294","citing_title":"Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2511.09425","citing_title":"Supporting Evidence for the Adaptive Feature Program across Diverse Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW","json":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW.json","graph_json":"https://pith.science/api/pith-number/MYC3LECPDTCYJNJKIL455DFBYW/graph.json","events_json":"https://pith.science/api/pith-number/MYC3LECPDTCYJNJKIL455DFBYW/events.json","paper":"https://pith.science/paper/MYC3LECP"},"agent_actions":{"view_html":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW","download_json":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW.json","view_paper":"https://pith.science/paper/MYC3LECP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18756&json=true","fetch_graph":"https://pith.science/api/pith-number/MYC3LECPDTCYJNJKIL455DFBYW/graph.json","fetch_events":"https://pith.science/api/pith-number/MYC3LECPDTCYJNJKIL455DFBYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW/action/storage_attestation","attest_author":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW/action/author_attestation","sign_citation":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW/action/citation_signature","submit_replication":"https://pith.science/pith/MYC3LECPDTCYJNJKIL455DFBYW/action/replication_record"}},"created_at":"2026-07-05T09:54:10.218429+00:00","updated_at":"2026-07-05T09:54:10.218429+00:00"}