{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DF2IES24W5RFLOT2IUNRGTHJQN","short_pith_number":"pith:DF2IES24","canonical_record":{"source":{"id":"1806.05393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T07:04:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"615738f32b0b0797dc95bab4e54e9d81b296d9c12d3c895267034e4a57d1ac92","abstract_canon_sha256":"85cedf24aaf743cbac9b02fc58bc55fbccc0979f576fcd0479ff06becd7b3b9e"},"schema_version":"1.0"},"canonical_sha256":"1974824b5cb76255ba7a451b134ce9834f4d41330a8c27e4d043a5eff1d12ab4","source":{"kind":"arxiv","id":"1806.05393","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05393","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05393v2","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05393","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"DF2IES24W5RF","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DF2IES24W5RFLOT2","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DF2IES24","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DF2IES24W5RFLOT2IUNRGTHJQN","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T07:04:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"615738f32b0b0797dc95bab4e54e9d81b296d9c12d3c895267034e4a57d1ac92","abstract_canon_sha256":"85cedf24aaf743cbac9b02fc58bc55fbccc0979f576fcd0479ff06becd7b3b9e"},"schema_version":"1.0"},"canonical_sha256":"1974824b5cb76255ba7a451b134ce9834f4d41330a8c27e4d043a5eff1d12ab4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:04.508394Z","signature_b64":"A6JaOMoAHoksU+JZfDJX+aO8WiKm40a/xl2oGC/BdzenMf8T9P6p9juScqjW6JyTPSUrxkJG5ze3HzRDrcz/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1974824b5cb76255ba7a451b134ce9834f4d41330a8c27e4d043a5eff1d12ab4","last_reissued_at":"2026-05-18T00:11:04.507713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:04.507713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05393","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gvkNnDe1nysqe2AtmUWeZok90VkOg7hlUb76REbJJyq3T9rcOmQmyGjHXq73VBZMSUXh4dexlShvjMMHO0ffBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:14:01.821837Z"},"content_sha256":"db911f908e0fa8785df31fbc0e3d69a16e434a4727b8155318d5f7c382a058ae","schema_version":"1.0","event_id":"sha256:db911f908e0fa8785df31fbc0e3d69a16e434a4727b8155318d5f7c382a058ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DF2IES24W5RFLOT2IUNRGTHJQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jascha Sohl-Dickstein, Jeffrey Pennington, Lechao Xiao, Samuel S. Schoenholz, Yasaman Bahri","submitted_at":"2018-06-14T07:04:15Z","abstract_excerpt":"In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful models employing hundreds or even thousands of layers. A variety of pathologies such as vanishing/exploding gradients make training such deep networks challenging. While residual connections and batch normalization do enable training at these depths, it has remained unclear whether such specialized architecture designs are truly necessary to train deep CNNs. In this work, we demonstrate that it is possible to train vani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05393","kind":"arxiv","version":2},"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":"2026-05-18T00:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YywC7TmIvPImh91zuEFYBSkE2S1T4nvaUH3vM3QINB6BsflLrGtOx6jFfy4rsyh3w9XgQNDDH1IcAzQyhYkWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:14:01.822184Z"},"content_sha256":"0a5388f0be96a2d1f3f68e4b33d0251d3c8ad38d0539b6d7b07793593a7c7ea4","schema_version":"1.0","event_id":"sha256:0a5388f0be96a2d1f3f68e4b33d0251d3c8ad38d0539b6d7b07793593a7c7ea4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DF2IES24W5RFLOT2IUNRGTHJQN/bundle.json","state_url":"https://pith.science/pith/DF2IES24W5RFLOT2IUNRGTHJQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DF2IES24W5RFLOT2IUNRGTHJQN/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":"2026-07-16T10:14:01Z","links":{"resolver":"https://pith.science/pith/DF2IES24W5RFLOT2IUNRGTHJQN","bundle":"https://pith.science/pith/DF2IES24W5RFLOT2IUNRGTHJQN/bundle.json","state":"https://pith.science/pith/DF2IES24W5RFLOT2IUNRGTHJQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DF2IES24W5RFLOT2IUNRGTHJQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DF2IES24W5RFLOT2IUNRGTHJQN","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":"85cedf24aaf743cbac9b02fc58bc55fbccc0979f576fcd0479ff06becd7b3b9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T07:04:15Z","title_canon_sha256":"615738f32b0b0797dc95bab4e54e9d81b296d9c12d3c895267034e4a57d1ac92"},"schema_version":"1.0","source":{"id":"1806.05393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05393","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05393v2","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05393","created_at":"2026-05-18T00:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"DF2IES24W5RF","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DF2IES24W5RFLOT2","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DF2IES24","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:0a5388f0be96a2d1f3f68e4b33d0251d3c8ad38d0539b6d7b07793593a7c7ea4","target":"graph","created_at":"2026-05-18T00:11:04Z","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":"In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful models employing hundreds or even thousands of layers. A variety of pathologies such as vanishing/exploding gradients make training such deep networks challenging. While residual connections and batch normalization do enable training at these depths, it has remained unclear whether such specialized architecture designs are truly necessary to train deep CNNs. In this work, we demonstrate that it is possible to train vani","authors_text":"Jascha Sohl-Dickstein, Jeffrey Pennington, Lechao Xiao, Samuel S. Schoenholz, Yasaman Bahri","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T07:04:15Z","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05393","kind":"arxiv","version":2},"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:db911f908e0fa8785df31fbc0e3d69a16e434a4727b8155318d5f7c382a058ae","target":"record","created_at":"2026-05-18T00:11:04Z","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":"85cedf24aaf743cbac9b02fc58bc55fbccc0979f576fcd0479ff06becd7b3b9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T07:04:15Z","title_canon_sha256":"615738f32b0b0797dc95bab4e54e9d81b296d9c12d3c895267034e4a57d1ac92"},"schema_version":"1.0","source":{"id":"1806.05393","kind":"arxiv","version":2}},"canonical_sha256":"1974824b5cb76255ba7a451b134ce9834f4d41330a8c27e4d043a5eff1d12ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1974824b5cb76255ba7a451b134ce9834f4d41330a8c27e4d043a5eff1d12ab4","first_computed_at":"2026-05-18T00:11:04.507713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:04.507713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A6JaOMoAHoksU+JZfDJX+aO8WiKm40a/xl2oGC/BdzenMf8T9P6p9juScqjW6JyTPSUrxkJG5ze3HzRDrcz/BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:04.508394Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db911f908e0fa8785df31fbc0e3d69a16e434a4727b8155318d5f7c382a058ae","sha256:0a5388f0be96a2d1f3f68e4b33d0251d3c8ad38d0539b6d7b07793593a7c7ea4"],"state_sha256":"c57ffcdb2bd06137becca28f095fa6ba3198368e60bc9b84f3311c221637d460"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jznmmF9Y0A+/B0u/GwTmrPx5lCrFmybwHZMLn7pW6WJk0UVf2fh/Rg5SWSX12kOrVIPzYc6T30QSyvs+LhjRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T10:14:01.824698Z","bundle_sha256":"6db4820f3cb6ad215a9f04fea72837717ba6490d1c93fbd04de93fea197c1c37"}}