{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X6GBHBRA43WH44SOB5V4KUMAWJ","short_pith_number":"pith:X6GBHBRA","schema_version":"1.0","canonical_sha256":"bf8c138620e6ec7e724e0f6bc55180b278e1099a4079faa61eb48d6ae81d985b","source":{"kind":"arxiv","id":"1911.00809","version":1},"attestation_state":"computed","paper":{"title":"Enhanced Convolutional Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingli Yu, Ruosong Wang, Ruslan Salakhutdinov, Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li","submitted_at":"2019-11-03T02:24:39Z","abstract_excerpt":"Recent research shows that for training with $\\ell_2$ loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspond to regression with respect to the CNN Gaussian Process kernel (CNN-GP) if only the last layer is trained, and correspond to regression with respect to the Convolutional Neural Tangent Kernel (CNTK) if all layers are trained. An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture"},"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":"1911.00809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T02:24:39Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"571b8720114d11daa8148456610a2fd02484a64502e12cf3310717d40c1bf6b8","abstract_canon_sha256":"703e2711b195ba799f75ce8b77dc68c3cfd7432841dc0ed11e56311ef2bd814f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:43.001775Z","signature_b64":"iM1ulEwZ1Ih1es+hHPaHZLlOsYyFgr2EoAPmPoRwiHntA41+5cL1bgJ+epE7OKflYISOV8JeW01dtSD1Zh3zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf8c138620e6ec7e724e0f6bc55180b278e1099a4079faa61eb48d6ae81d985b","last_reissued_at":"2026-07-05T00:16:43.001426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:43.001426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced Convolutional Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingli Yu, Ruosong Wang, Ruslan Salakhutdinov, Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li","submitted_at":"2019-11-03T02:24:39Z","abstract_excerpt":"Recent research shows that for training with $\\ell_2$ loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspond to regression with respect to the CNN Gaussian Process kernel (CNN-GP) if only the last layer is trained, and correspond to regression with respect to the Convolutional Neural Tangent Kernel (CNTK) if all layers are trained. An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00809","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/1911.00809/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":"1911.00809","created_at":"2026-07-05T00:16:43.001485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00809v1","created_at":"2026-07-05T00:16:43.001485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00809","created_at":"2026-07-05T00:16:43.001485+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6GBHBRA43WH","created_at":"2026-07-05T00:16:43.001485+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6GBHBRA43WH44SO","created_at":"2026-07-05T00:16:43.001485+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6GBHBRA","created_at":"2026-07-05T00:16:43.001485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15127","citing_title":"Towards Source-Free Machine Unlearning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ","json":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ.json","graph_json":"https://pith.science/api/pith-number/X6GBHBRA43WH44SOB5V4KUMAWJ/graph.json","events_json":"https://pith.science/api/pith-number/X6GBHBRA43WH44SOB5V4KUMAWJ/events.json","paper":"https://pith.science/paper/X6GBHBRA"},"agent_actions":{"view_html":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ","download_json":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ.json","view_paper":"https://pith.science/paper/X6GBHBRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00809&json=true","fetch_graph":"https://pith.science/api/pith-number/X6GBHBRA43WH44SOB5V4KUMAWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/X6GBHBRA43WH44SOB5V4KUMAWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ/action/storage_attestation","attest_author":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ/action/author_attestation","sign_citation":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ/action/citation_signature","submit_replication":"https://pith.science/pith/X6GBHBRA43WH44SOB5V4KUMAWJ/action/replication_record"}},"created_at":"2026-07-05T00:16:43.001485+00:00","updated_at":"2026-07-05T00:16:43.001485+00:00"}