{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MGIODE4TPSLL55T6GLICW6TI3E","short_pith_number":"pith:MGIODE4T","schema_version":"1.0","canonical_sha256":"6190e193937c96bef67e32d02b7a68d90e0d63f5eb53c11bc3997254bc5af3f9","source":{"kind":"arxiv","id":"2206.08720","version":1},"attestation_state":"computed","paper":{"title":"Fast Finite Width Neural Tangent Kernel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Roman Novak, Samuel S. Schoenholz","submitted_at":"2022-06-17T12:18:22Z","abstract_excerpt":"The Neural Tangent Kernel (NTK), defined as $\\Theta_\\theta^f(x_1, x_2) = \\left[\\partial f(\\theta, x_1)\\big/\\partial \\theta\\right] \\left[\\partial f(\\theta, x_2)\\big/\\partial \\theta\\right]^T$ where $\\left[\\partial f(\\theta, \\cdot)\\big/\\partial \\theta\\right]$ is a neural network (NN) Jacobian, has emerged as a central object of study in deep learning. In the infinite width limit, the NTK can sometimes be computed analytically and is useful for understanding training and generalization of NN architectures. At finite widths, the NTK is also used to better initialize NNs, compare the conditioning ac"},"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":"2206.08720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T12:18:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0965d590a8eeaa00b3999bf8237f02acf501de9c6c2ac68e413b211705ae33f1","abstract_canon_sha256":"4b20c6c27b87518478c330176780b100450a2b918671625a04cbb3966e68529b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:42.472388Z","signature_b64":"hjs5AJfebBvnqhoG3xpHWKCMPnBWV9MuVdbUFPZsTJYI+1d+4+6PHcnZoqB0j/KdJwQ/Ykk951m0j4xgnoqgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6190e193937c96bef67e32d02b7a68d90e0d63f5eb53c11bc3997254bc5af3f9","last_reissued_at":"2026-07-05T04:32:42.471895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:42.471895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Finite Width Neural Tangent Kernel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Roman Novak, Samuel S. Schoenholz","submitted_at":"2022-06-17T12:18:22Z","abstract_excerpt":"The Neural Tangent Kernel (NTK), defined as $\\Theta_\\theta^f(x_1, x_2) = \\left[\\partial f(\\theta, x_1)\\big/\\partial \\theta\\right] \\left[\\partial f(\\theta, x_2)\\big/\\partial \\theta\\right]^T$ where $\\left[\\partial f(\\theta, \\cdot)\\big/\\partial \\theta\\right]$ is a neural network (NN) Jacobian, has emerged as a central object of study in deep learning. In the infinite width limit, the NTK can sometimes be computed analytically and is useful for understanding training and generalization of NN architectures. At finite widths, the NTK is also used to better initialize NNs, compare the conditioning ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08720","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/2206.08720/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":"2206.08720","created_at":"2026-07-05T04:32:42.471954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08720v1","created_at":"2026-07-05T04:32:42.471954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08720","created_at":"2026-07-05T04:32:42.471954+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGIODE4TPSLL","created_at":"2026-07-05T04:32:42.471954+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGIODE4TPSLL55T6","created_at":"2026-07-05T04:32:42.471954+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGIODE4T","created_at":"2026-07-05T04:32:42.471954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08377","citing_title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","ref_index":285,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E","json":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E.json","graph_json":"https://pith.science/api/pith-number/MGIODE4TPSLL55T6GLICW6TI3E/graph.json","events_json":"https://pith.science/api/pith-number/MGIODE4TPSLL55T6GLICW6TI3E/events.json","paper":"https://pith.science/paper/MGIODE4T"},"agent_actions":{"view_html":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E","download_json":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E.json","view_paper":"https://pith.science/paper/MGIODE4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08720&json=true","fetch_graph":"https://pith.science/api/pith-number/MGIODE4TPSLL55T6GLICW6TI3E/graph.json","fetch_events":"https://pith.science/api/pith-number/MGIODE4TPSLL55T6GLICW6TI3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E/action/storage_attestation","attest_author":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E/action/author_attestation","sign_citation":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E/action/citation_signature","submit_replication":"https://pith.science/pith/MGIODE4TPSLL55T6GLICW6TI3E/action/replication_record"}},"created_at":"2026-07-05T04:32:42.471954+00:00","updated_at":"2026-07-05T04:32:42.471954+00:00"}