{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LQELKQKXEFWCG7TJ55B4V2XLCJ","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":"ed0c704ee768e08c01e45cf1cca1cfb8f4fe811a9c44967a1d95310b86392b79","cross_cats_sorted":["cs.LG","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-11T13:17:22Z","title_canon_sha256":"9c1b99ab75f9a8356b87a57ea69bc8fe8b6908dc0f37639898f3bb2a934d9c6c"},"schema_version":"1.0","source":{"id":"1801.03744","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03744","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03744v3","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03744","created_at":"2026-05-18T00:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"LQELKQKXEFWC","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LQELKQKXEFWCG7TJ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LQELKQKX","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:4d6937fd3a80ad24b45e8bb282e1f03b39d98d1c99043c56c230fb0cca652bcc","target":"graph","created_at":"2026-05-18T00:02:13Z","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":"We give a rigorous analysis of the statistical behavior of gradients in a randomly initialized fully connected network N with ReLU activations. Our results show that the empirical variance of the squares of the entries in the input-output Jacobian of N is exponential in a simple architecture-dependent constant beta, given by the sum of the reciprocals of the hidden layer widths. When beta is large, the gradients computed by N at initialization vary wildly. Our approach complements the mean field theory analysis of random networks. From this point of view, we rigorously compute finite width cor","authors_text":"Boris Hanin","cross_cats":["cs.LG","math.PR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-11T13:17:22Z","title":"Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03744","kind":"arxiv","version":3},"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:c17a9a00e8264687091b4585d909247f40efe535e5f12378061a6d65bfe96399","target":"record","created_at":"2026-05-18T00:02:13Z","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":"ed0c704ee768e08c01e45cf1cca1cfb8f4fe811a9c44967a1d95310b86392b79","cross_cats_sorted":["cs.LG","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-11T13:17:22Z","title_canon_sha256":"9c1b99ab75f9a8356b87a57ea69bc8fe8b6908dc0f37639898f3bb2a934d9c6c"},"schema_version":"1.0","source":{"id":"1801.03744","kind":"arxiv","version":3}},"canonical_sha256":"5c08b54157216c237e69ef43caeaeb127dce9bcce02d8afd6f4200be312b346c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c08b54157216c237e69ef43caeaeb127dce9bcce02d8afd6f4200be312b346c","first_computed_at":"2026-05-18T00:02:13.020629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:13.020629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UVR6blydDgzqvx+gyiwd/vxDeEubX53++8qqcVLKXmNjCo6HUNnPZvG4sny6UsW4gcTHvvk8OAlM6TNUuScCBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:13.021277Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.03744","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c17a9a00e8264687091b4585d909247f40efe535e5f12378061a6d65bfe96399","sha256:4d6937fd3a80ad24b45e8bb282e1f03b39d98d1c99043c56c230fb0cca652bcc"],"state_sha256":"5501c913cbb66213baf8ab436587bde879fe31b2a07e4f71da72c66141353923"}