{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:L6KURNLZM2EK4B6NZ3TWJXNZNH","short_pith_number":"pith:L6KURNLZ","canonical_record":{"source":{"id":"1905.10157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T11:33:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0767d5b888ed51312288845e8ab475a44c22a6ff16ca1151b496b0064060b37f","abstract_canon_sha256":"a01fb7863528723de3a099ae359ba764d7ad2f5456e6278df3ebaf3fd6641f78"},"schema_version":"1.0"},"canonical_sha256":"5f9548b5796688ae07cdcee764ddb969f606b7041425d299ef37436b7d7d278a","source":{"kind":"arxiv","id":"1905.10157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10157","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10157v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10157","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"L6KURNLZM2EK","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L6KURNLZM2EK4B6N","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L6KURNLZ","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:L6KURNLZM2EK4B6NZ3TWJXNZNH","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T11:33:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0767d5b888ed51312288845e8ab475a44c22a6ff16ca1151b496b0064060b37f","abstract_canon_sha256":"a01fb7863528723de3a099ae359ba764d7ad2f5456e6278df3ebaf3fd6641f78"},"schema_version":"1.0"},"canonical_sha256":"5f9548b5796688ae07cdcee764ddb969f606b7041425d299ef37436b7d7d278a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:11.198025Z","signature_b64":"PSHqqla028F8WsIOaZzvEuKPAYeQeOn5YlyZfYVF93x1ltglDwzxEBv+IsS7TRqLVjNq55pEh2n6aONpQPuoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f9548b5796688ae07cdcee764ddb969f606b7041425d299ef37436b7d7d278a","last_reissued_at":"2026-05-17T23:45:11.197438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:11.197438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10157","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":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHY/brtevWItmy/TA/hC1JMzsoM8YTXKPR+PdAv9OedQn+f3f0B1zLvgtZJqUWpDOuaHW3pGKa8kPo/Cy7FtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:02:48.135670Z"},"content_sha256":"18227c0b29d26352870cbcd044426f70cbbe3052a3365898d27786d78c20df1a","schema_version":"1.0","event_id":"sha256:18227c0b29d26352870cbcd044426f70cbbe3052a3365898d27786d78c20df1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:L6KURNLZM2EK4B6NZ3TWJXNZNH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Yu, Junzhao Zhang, Zhanxing Zhu","submitted_at":"2019-05-24T11:33:13Z","abstract_excerpt":"Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step toward understanding the success of CNNs by investigating the learning dynamics of a two-layer nonlinear convolutional neural network over some specific data distributions. Rather than the typical Gaussian assumption for input data distribution, we consider a more realistic setting that each data point (e.g. image) contains a specific pattern determining it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10157","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":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zvcfylb2j9PNAtbx21K5tjdnngJuyY2sezcGsoanJpyoYWKMp9a8KsuGFvzqNzD5neSKjvrAOJRapE3XmL6ZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:02:48.136023Z"},"content_sha256":"65c1e4f2ee5dc6970a522c80e6bb383c321ca1a7fb344d3199d160560880ac2e","schema_version":"1.0","event_id":"sha256:65c1e4f2ee5dc6970a522c80e6bb383c321ca1a7fb344d3199d160560880ac2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/bundle.json","state_url":"https://pith.science/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/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":"2026-05-30T16:02:48Z","links":{"resolver":"https://pith.science/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH","bundle":"https://pith.science/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/bundle.json","state":"https://pith.science/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6KURNLZM2EK4B6NZ3TWJXNZNH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L6KURNLZM2EK4B6NZ3TWJXNZNH","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":"a01fb7863528723de3a099ae359ba764d7ad2f5456e6278df3ebaf3fd6641f78","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T11:33:13Z","title_canon_sha256":"0767d5b888ed51312288845e8ab475a44c22a6ff16ca1151b496b0064060b37f"},"schema_version":"1.0","source":{"id":"1905.10157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10157","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10157v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10157","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"L6KURNLZM2EK","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L6KURNLZM2EK4B6N","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L6KURNLZ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:65c1e4f2ee5dc6970a522c80e6bb383c321ca1a7fb344d3199d160560880ac2e","target":"graph","created_at":"2026-05-17T23:45:11Z","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":"Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step toward understanding the success of CNNs by investigating the learning dynamics of a two-layer nonlinear convolutional neural network over some specific data distributions. Rather than the typical Gaussian assumption for input data distribution, we consider a more realistic setting that each data point (e.g. image) contains a specific pattern determining it","authors_text":"Bing Yu, Junzhao Zhang, Zhanxing Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T11:33:13Z","title":"On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10157","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":"sha256:18227c0b29d26352870cbcd044426f70cbbe3052a3365898d27786d78c20df1a","target":"record","created_at":"2026-05-17T23:45:11Z","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":"a01fb7863528723de3a099ae359ba764d7ad2f5456e6278df3ebaf3fd6641f78","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T11:33:13Z","title_canon_sha256":"0767d5b888ed51312288845e8ab475a44c22a6ff16ca1151b496b0064060b37f"},"schema_version":"1.0","source":{"id":"1905.10157","kind":"arxiv","version":1}},"canonical_sha256":"5f9548b5796688ae07cdcee764ddb969f606b7041425d299ef37436b7d7d278a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f9548b5796688ae07cdcee764ddb969f606b7041425d299ef37436b7d7d278a","first_computed_at":"2026-05-17T23:45:11.197438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:11.197438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSHqqla028F8WsIOaZzvEuKPAYeQeOn5YlyZfYVF93x1ltglDwzxEBv+IsS7TRqLVjNq55pEh2n6aONpQPuoCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:11.198025Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18227c0b29d26352870cbcd044426f70cbbe3052a3365898d27786d78c20df1a","sha256:65c1e4f2ee5dc6970a522c80e6bb383c321ca1a7fb344d3199d160560880ac2e"],"state_sha256":"4d4c05b10730b1a08e5335093c410043cbf7b8f1745950edcd0764635e74b818"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LK8WWBg9Iztdmlhh9hHxCrI1++h8dmREXbu6liLk5zBDMYapTxydDjsylJY5i0qyu4gt4CwkIzxoLJo4Afb0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:02:48.138674Z","bundle_sha256":"398e61312d08ea9dac0ae8980b51da54bff1336d10933803bfd390296c0c31e0"}}