{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z4BUPOAAWOZIZW5B43SWDBZ7NU","short_pith_number":"pith:Z4BUPOAA","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"},"canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","source":{"kind":"arxiv","id":"2007.03714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03714","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03714v1","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03714","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z4BUPOAAWOZI","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z4BUPOAAWOZIZW5B","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z4BUPOAA","created_at":"2026-07-05T06:14:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z4BUPOAAWOZIZW5B43SWDBZ7NU","target":"record","payload":{"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"},"canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","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"},"source_kind":"arxiv","source_id":"2007.03714","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c0Fapy7zt9zEM4gqqYDAoHc3KK7yaq/ftwrsRRXpPE2uYsEFls9yHYDNwFCwyOhmz9dhoGnACYg7vbg5UgVgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:14:29.391830Z"},"content_sha256":"23e83407dbf8ae674606c09db4560c41dc51bbe6f28fc7a25e2ed736fe7ffade","schema_version":"1.0","event_id":"sha256:23e83407dbf8ae674606c09db4560c41dc51bbe6f28fc7a25e2ed736fe7ffade"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z4BUPOAAWOZIZW5B43SWDBZ7NU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VqvMeI2GhE2x8cIWrowg/QGH7TvY/fRPEfp47ELFqvtoD3sSynL030LBoKOKuRuA6qywfq39ZQIVvW8Kuk7BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:14:29.392363Z"},"content_sha256":"5223dbfa3a45db89553952c8701743b9c733bf37b33f3032bf7385fa1072dc50","schema_version":"1.0","event_id":"sha256:5223dbfa3a45db89553952c8701743b9c733bf37b33f3032bf7385fa1072dc50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/bundle.json","state_url":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T18:14:29Z","links":{"resolver":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU","bundle":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/bundle.json","state":"https://pith.science/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4BUPOAAWOZIZW5B43SWDBZ7NU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z4BUPOAAWOZIZW5B43SWDBZ7NU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"330b974965d2f4557fc99ebe4cf71c1ab3f704b7f12d28004f033a58cd22f055","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T18:08:16Z","title_canon_sha256":"280e943b928f2b23a69e856c5ac4ef849bae34385fe5443d0306680783a6be4e"},"schema_version":"1.0","source":{"id":"2007.03714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03714","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03714v1","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03714","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z4BUPOAAWOZI","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z4BUPOAAWOZIZW5B","created_at":"2026-07-05T06:14:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z4BUPOAA","created_at":"2026-07-05T06:14:02Z"}],"graph_snapshots":[{"event_id":"sha256:5223dbfa3a45db89553952c8701743b9c733bf37b33f3032bf7385fa1072dc50","target":"graph","created_at":"2026-07-05T06:14:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.03714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Nung Kwan Yip, Tao Luo, Yuqing Li","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T18:08:16Z","title":"Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03714","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:23e83407dbf8ae674606c09db4560c41dc51bbe6f28fc7a25e2ed736fe7ffade","target":"record","created_at":"2026-07-05T06:14:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"330b974965d2f4557fc99ebe4cf71c1ab3f704b7f12d28004f033a58cd22f055","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T18:08:16Z","title_canon_sha256":"280e943b928f2b23a69e856c5ac4ef849bae34385fe5443d0306680783a6be4e"},"schema_version":"1.0","source":{"id":"2007.03714","kind":"arxiv","version":1}},"canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf0347b800b3b28cdba1e6e561873f6d2e7e314ac39d0d82dc415342d98ee711","first_computed_at":"2026-07-05T06:14:02.024438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:02.024438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ZdlZDR1NoQeyPmDTz9dvfrxaXq7P4g2gHHZvvAFlsTwrStEtFJ3Lkaoaa1OginC9mdvbPVlguucEoSiQqwiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:02.024931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23e83407dbf8ae674606c09db4560c41dc51bbe6f28fc7a25e2ed736fe7ffade","sha256:5223dbfa3a45db89553952c8701743b9c733bf37b33f3032bf7385fa1072dc50"],"state_sha256":"bdfb6718f59fdade47a5f804252385f8adca8439e0c167b7a1b44800c5f249ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KCF84gixPA5wY7bplzTXXFmMree38FjtlhKS9BROsxJRacNBSSvQVlqmSqs/nWtRifGRaHpHlU+ro10zWXmDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:14:29.397240Z","bundle_sha256":"12c64b7bfa1b52623bd34319c4fa23b29b37a392ee3d3249f13f798f646607a6"}}