{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CJBDPWFMFQFSYSJYJ3ZGFEWX3E","short_pith_number":"pith:CJBDPWFM","schema_version":"1.0","canonical_sha256":"124237d8ac2c0b2c49384ef26292d7d913825cd2a82361be652a623bd63031ff","source":{"kind":"arxiv","id":"1905.12173","version":2},"attestation_state":"computed","paper":{"title":"On the Inductive Bias of Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Bietti, Julien Mairal","submitted_at":"2019-05-29T01:49:32Z","abstract_excerpt":"State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain over-parameterized regime, the learning dynamics of gradient descent are governed by a certain kernel obtained at initialization, called the neural tangent kernel. We study the inductive bias of learning in such a regime by analyzing this kernel and the corresponding function space (RKHS). In particular, we study smoothness, approximation, and stability proper"},"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":"1905.12173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-29T01:49:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eff302391f8f7135adc7bdf8b01ffca63aee1920a16fa14a47d037b5386aebe5","abstract_canon_sha256":"0ba85558280961062d6b533bed1b23c2a32ad3e171add338cab313900761ae12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:04.075865Z","signature_b64":"8+UoJint7AShIj39M7e3m+e/7H1iAkR92cprH3YgXgVVu7b7yQl/pAZrzSXHcfMzKiv9ySoSDCpfqoVG9DvwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"124237d8ac2c0b2c49384ef26292d7d913825cd2a82361be652a623bd63031ff","last_reissued_at":"2026-07-05T00:16:04.075449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:04.075449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Inductive Bias of Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Bietti, Julien Mairal","submitted_at":"2019-05-29T01:49:32Z","abstract_excerpt":"State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain over-parameterized regime, the learning dynamics of gradient descent are governed by a certain kernel obtained at initialization, called the neural tangent kernel. We study the inductive bias of learning in such a regime by analyzing this kernel and the corresponding function space (RKHS). In particular, we study smoothness, approximation, and stability proper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12173","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/1905.12173/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":"1905.12173","created_at":"2026-07-05T00:16:04.075506+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12173v2","created_at":"2026-07-05T00:16:04.075506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12173","created_at":"2026-07-05T00:16:04.075506+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJBDPWFMFQFS","created_at":"2026-07-05T00:16:04.075506+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJBDPWFMFQFSYSJY","created_at":"2026-07-05T00:16:04.075506+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJBDPWFM","created_at":"2026-07-05T00:16:04.075506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18686","citing_title":"Neural Spectral Bias and Conformal Correlators I: Introduction and Applications","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18673","citing_title":"Neural Networks Reveal a Universal Bias in Conformal Correlators","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E","json":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E.json","graph_json":"https://pith.science/api/pith-number/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/graph.json","events_json":"https://pith.science/api/pith-number/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/events.json","paper":"https://pith.science/paper/CJBDPWFM"},"agent_actions":{"view_html":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E","download_json":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E.json","view_paper":"https://pith.science/paper/CJBDPWFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12173&json=true","fetch_graph":"https://pith.science/api/pith-number/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/graph.json","fetch_events":"https://pith.science/api/pith-number/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/action/storage_attestation","attest_author":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/action/author_attestation","sign_citation":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/action/citation_signature","submit_replication":"https://pith.science/pith/CJBDPWFMFQFSYSJYJ3ZGFEWX3E/action/replication_record"}},"created_at":"2026-07-05T00:16:04.075506+00:00","updated_at":"2026-07-05T00:16:04.075506+00:00"}