{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3A6L3XDV3JE2BU5HX2O3QOPWAW","short_pith_number":"pith:3A6L3XDV","canonical_record":{"source":{"id":"1812.00174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-01T08:12:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a2ef9990c988d27caeece3ee882d006e7f32cb1a52864b6bdce3b5a5723b7b7","abstract_canon_sha256":"2df91538b819fb955ac0d8ed5c785b04b3be93b12ba7d4de6240bfa48df6cbbf"},"schema_version":"1.0"},"canonical_sha256":"d83cbddc75da49a0d3a7be9db839f605986163bada71ffa5c4fc201801ff90f3","source":{"kind":"arxiv","id":"1812.00174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00174","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00174v1","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00174","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"3A6L3XDV3JE2","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3A6L3XDV3JE2BU5H","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3A6L3XDV","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3A6L3XDV3JE2BU5HX2O3QOPWAW","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-01T08:12:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a2ef9990c988d27caeece3ee882d006e7f32cb1a52864b6bdce3b5a5723b7b7","abstract_canon_sha256":"2df91538b819fb955ac0d8ed5c785b04b3be93b12ba7d4de6240bfa48df6cbbf"},"schema_version":"1.0"},"canonical_sha256":"d83cbddc75da49a0d3a7be9db839f605986163bada71ffa5c4fc201801ff90f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:27.000635Z","signature_b64":"pQmu7Ae8kMMrcMhGYof+d38ZenNC7oTwFHH0NLDYKuCqJFRTIGMwEeA7uc7TMYjd59qF4JkzfFbWEoLXqS2tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d83cbddc75da49a0d3a7be9db839f605986163bada71ffa5c4fc201801ff90f3","last_reissued_at":"2026-05-17T23:59:27.000001Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:27.000001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00174","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":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"em+v4+zDV4UQ6E5JN6g7WciwAYSpIgjMkBjtFPySDASDaw7VwKcw2yBpiV0VjlpJDklTNDW9Mdgwdst7ZR7zDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:06:40.354477Z"},"content_sha256":"a063213486ce00013136d19f0f18f3f92cde186a2422be14001d8ac464efd540","schema_version":"1.0","event_id":"sha256:a063213486ce00013136d19f0f18f3f92cde186a2422be14001d8ac464efd540"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3A6L3XDV3JE2BU5HX2O3QOPWAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Training of Residual Networks: a Differential Equation Viewpoint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiang Du, Qi Sun, Yunzhe Tao","submitted_at":"2018-12-01T08:12:01Z","abstract_excerpt":"During the last few years, significant attention has been paid to the stochastic training of artificial neural networks, which is known as an effective regularization approach that helps improve the generalization capability of trained models. In this work, the method of modified equations is applied to show that the residual network and its variants with noise injection can be regarded as weak approximations of stochastic differential equations. Such observations enable us to bridge the stochastic training processes with the optimal control of backward Kolmogorov's equations. This not only of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00174","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":""},"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":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLgvvk9E52M1W3YSSeMCGUNBUAf/efVM0EGlIIKmW2goAnPVv0Ci9/pf1skbFIh132aU/+JxRyzx4hOW3os0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:06:40.355177Z"},"content_sha256":"a6a8f8183ab76a625b41bdd36f1d40cb203e7b57ed90a5fb2ce545e4d5b5fa84","schema_version":"1.0","event_id":"sha256:a6a8f8183ab76a625b41bdd36f1d40cb203e7b57ed90a5fb2ce545e4d5b5fa84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/bundle.json","state_url":"https://pith.science/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/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":"2026-06-09T05:06:40Z","links":{"resolver":"https://pith.science/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW","bundle":"https://pith.science/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/bundle.json","state":"https://pith.science/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3A6L3XDV3JE2BU5HX2O3QOPWAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3A6L3XDV3JE2BU5HX2O3QOPWAW","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":"2df91538b819fb955ac0d8ed5c785b04b3be93b12ba7d4de6240bfa48df6cbbf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-01T08:12:01Z","title_canon_sha256":"9a2ef9990c988d27caeece3ee882d006e7f32cb1a52864b6bdce3b5a5723b7b7"},"schema_version":"1.0","source":{"id":"1812.00174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00174","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00174v1","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00174","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"3A6L3XDV3JE2","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3A6L3XDV3JE2BU5H","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3A6L3XDV","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:a6a8f8183ab76a625b41bdd36f1d40cb203e7b57ed90a5fb2ce545e4d5b5fa84","target":"graph","created_at":"2026-05-17T23:59:27Z","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"},"paper":{"abstract_excerpt":"During the last few years, significant attention has been paid to the stochastic training of artificial neural networks, which is known as an effective regularization approach that helps improve the generalization capability of trained models. In this work, the method of modified equations is applied to show that the residual network and its variants with noise injection can be regarded as weak approximations of stochastic differential equations. Such observations enable us to bridge the stochastic training processes with the optimal control of backward Kolmogorov's equations. This not only of","authors_text":"Qiang Du, Qi Sun, Yunzhe Tao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-01T08:12:01Z","title":"Stochastic Training of Residual Networks: a Differential Equation Viewpoint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00174","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:a063213486ce00013136d19f0f18f3f92cde186a2422be14001d8ac464efd540","target":"record","created_at":"2026-05-17T23:59:27Z","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":"2df91538b819fb955ac0d8ed5c785b04b3be93b12ba7d4de6240bfa48df6cbbf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-01T08:12:01Z","title_canon_sha256":"9a2ef9990c988d27caeece3ee882d006e7f32cb1a52864b6bdce3b5a5723b7b7"},"schema_version":"1.0","source":{"id":"1812.00174","kind":"arxiv","version":1}},"canonical_sha256":"d83cbddc75da49a0d3a7be9db839f605986163bada71ffa5c4fc201801ff90f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d83cbddc75da49a0d3a7be9db839f605986163bada71ffa5c4fc201801ff90f3","first_computed_at":"2026-05-17T23:59:27.000001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:27.000001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQmu7Ae8kMMrcMhGYof+d38ZenNC7oTwFHH0NLDYKuCqJFRTIGMwEeA7uc7TMYjd59qF4JkzfFbWEoLXqS2tCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:27.000635Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a063213486ce00013136d19f0f18f3f92cde186a2422be14001d8ac464efd540","sha256:a6a8f8183ab76a625b41bdd36f1d40cb203e7b57ed90a5fb2ce545e4d5b5fa84"],"state_sha256":"974d00d7c059ab88b403d0a7c2d2e70d95d264b4642f876ad69ae091eb8909d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9FYrslqdSY9KpNYNlF7UQ4r0nT+j/gWpgdj/xrMJX1EIvZmmkVDukQVkxlwDE2i7y6M68dp5C54Dmvbq7pAbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T05:06:40.359083Z","bundle_sha256":"677197956bae2395ca0ae05a598425e30740152dd467b5c1aaa36e965b03e6f8"}}