{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3OVCADLH66WPVXZWUCZ6SNTUU","short_pith_number":"pith:V3OVCADL","schema_version":"1.0","canonical_sha256":"aedd51006b3fbd67d6f9b5059f49b3a5284662fc07dfa677bb3ec13e63faae42","source":{"kind":"arxiv","id":"2602.23039","version":2},"attestation_state":"computed","paper":{"title":"Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Jakob Kramp, Javed Lindner, Moritz Helias","submitted_at":"2026-02-26T14:24:11Z","abstract_excerpt":"Training large neural networks exposes neural scaling laws for the generalization error, which points to a universal behavior across network architectures of learning in high dimensions. It was also shown that this effect persists in the limit of highly overparametrized networks as well as the Neural network Gaussian process limit. We here develop a principled understanding of the typical behavior of generalization in Neural Network Gaussian process regression dynamics. We derive a dynamical mean-field theory that captures the typical case learning dynamics: This allows us to unify multiple ex"},"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":"2602.23039","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-02-26T14:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"00d8895ab65dcb07fbf4e99839ec810e0391b3c1f17ae8bfb2ae729c167378f5","abstract_canon_sha256":"c061a315e42d257f687afd93888d0d340f0d9ced5d9092c8d2a95e6ffc2192a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:51.772010Z","signature_b64":"T//61XNOskfFBOb2auT0UD4W/3f+NXWYpj3tcmVYnJrnQIntvrNtcckLDx5NDzhdrMt3k6oZRKQZonnuIHHbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aedd51006b3fbd67d6f9b5059f49b3a5284662fc07dfa677bb3ec13e63faae42","last_reissued_at":"2026-06-02T02:04:51.771564Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:51.771564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Jakob Kramp, Javed Lindner, Moritz Helias","submitted_at":"2026-02-26T14:24:11Z","abstract_excerpt":"Training large neural networks exposes neural scaling laws for the generalization error, which points to a universal behavior across network architectures of learning in high dimensions. It was also shown that this effect persists in the limit of highly overparametrized networks as well as the Neural network Gaussian process limit. We here develop a principled understanding of the typical behavior of generalization in Neural Network Gaussian process regression dynamics. We derive a dynamical mean-field theory that captures the typical case learning dynamics: This allows us to unify multiple ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23039","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/2602.23039/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":"2602.23039","created_at":"2026-06-02T02:04:51.771624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23039v2","created_at":"2026-06-02T02:04:51.771624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23039","created_at":"2026-06-02T02:04:51.771624+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3OVCADLH66W","created_at":"2026-06-02T02:04:51.771624+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3OVCADLH66WPVXZ","created_at":"2026-06-02T02:04:51.771624+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3OVCADL","created_at":"2026-06-02T02:04:51.771624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU","json":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU.json","graph_json":"https://pith.science/api/pith-number/V3OVCADLH66WPVXZWUCZ6SNTUU/graph.json","events_json":"https://pith.science/api/pith-number/V3OVCADLH66WPVXZWUCZ6SNTUU/events.json","paper":"https://pith.science/paper/V3OVCADL"},"agent_actions":{"view_html":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU","download_json":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU.json","view_paper":"https://pith.science/paper/V3OVCADL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23039&json=true","fetch_graph":"https://pith.science/api/pith-number/V3OVCADLH66WPVXZWUCZ6SNTUU/graph.json","fetch_events":"https://pith.science/api/pith-number/V3OVCADLH66WPVXZWUCZ6SNTUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU/action/storage_attestation","attest_author":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU/action/author_attestation","sign_citation":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU/action/citation_signature","submit_replication":"https://pith.science/pith/V3OVCADLH66WPVXZWUCZ6SNTUU/action/replication_record"}},"created_at":"2026-06-02T02:04:51.771624+00:00","updated_at":"2026-06-02T02:04:51.771624+00:00"}