{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z4BUPOAAWOZIZW5B43SWDBZ7NU","short_pith_number":"pith:Z4BUPOAA","schema_version":"1.0","canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","source":{"kind":"arxiv","id":"2007.03714","version":1},"attestation_state":"computed","paper":{"title":"Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Nung Kwan Yip, Tao Luo, Yuqing Li","submitted_at":"2020-07-07T18:08:16Z","abstract_excerpt":"Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by the Neural Tangent Kernel (NTK) introduced in \\cite{Jacot2018Neural}. In this paper, we study dynamics of the NTK for finite width Deep Residual Network (ResNet) using the neural tangent hierarchy (NTH) proposed in \\cite{Huang2019Dynamics}. For a ResNet with smooth and Lipschitz activation function, we reduce the requirement on the layer width $m$ with respe"},"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":"2007.03714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T18:08:16Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"280e943b928f2b23a69e856c5ac4ef849bae34385fe5443d0306680783a6be4e","abstract_canon_sha256":"330b974965d2f4557fc99ebe4cf71c1ab3f704b7f12d28004f033a58cd22f055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:02.024931Z","signature_b64":"0ZdlZDR1NoQeyPmDTz9dvfrxaXq7P4g2gHHZvvAFlsTwrStEtFJ3Lkaoaa1OginC9mdvbPVlguucEoSiQqwiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","last_reissued_at":"2026-07-05T06:14:02.024438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:02.024438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Nung Kwan Yip, Tao Luo, Yuqing Li","submitted_at":"2020-07-07T18:08:16Z","abstract_excerpt":"Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by the Neural Tangent Kernel (NTK) introduced in \\cite{Jacot2018Neural}. In this paper, we study dynamics of the NTK for finite width Deep Residual Network (ResNet) using the neural tangent hierarchy (NTH) proposed in \\cite{Huang2019Dynamics}. For a ResNet with smooth and Lipschitz activation function, we reduce the requirement on the layer width $m$ with respe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03714","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/2007.03714/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":"2007.03714","created_at":"2026-07-05T06:14:02.024496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03714v1","created_at":"2026-07-05T06:14:02.024496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03714","created_at":"2026-07-05T06:14:02.024496+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4BUPOAAWOZI","created_at":"2026-07-05T06:14:02.024496+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4BUPOAAWOZIZW5B","created_at":"2026-07-05T06:14:02.024496+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4BUPOAA","created_at":"2026-07-05T06:14:02.024496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00488","citing_title":"Learn Singularly Perturbed Solutions via Homotopy Dynamics","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU","json":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU.json","graph_json":"https://pith.science/api/pith-number/Z4BUPOAAWOZIZW5B43SWDBZ7NU/graph.json","events_json":"https://pith.science/api/pith-number/Z4BUPOAAWOZIZW5B43SWDBZ7NU/events.json","paper":"https://pith.science/paper/Z4BUPOAA"},"agent_actions":{"view_html":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU","download_json":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU.json","view_paper":"https://pith.science/paper/Z4BUPOAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03714&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4BUPOAAWOZIZW5B43SWDBZ7NU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4BUPOAAWOZIZW5B43SWDBZ7NU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/action/storage_attestation","attest_author":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/action/author_attestation","sign_citation":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/action/citation_signature","submit_replication":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/action/replication_record"}},"created_at":"2026-07-05T06:14:02.024496+00:00","updated_at":"2026-07-05T06:14:02.024496+00:00"}