{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:HI6ITF3Y635V2HQQSYT5ZYCGPC","short_pith_number":"pith:HI6ITF3Y","canonical_record":{"source":{"id":"1412.6630","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T07:59:14Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"e0b953699d5d935fd14d0716e2d1ffe6a3f8b175896a7c38508902cb35bf7c2d","abstract_canon_sha256":"1cfc2bd3783fdffe3cc2c515d8dd4b38e6bd3fea478a498b4aa4db5424a4dd96"},"schema_version":"1.0"},"canonical_sha256":"3a3c899778f6fb5d1e109627dce04678b99e7a05699bd86c25118ca8db2f8b54","source":{"kind":"arxiv","id":"1412.6630","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6630","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6630v2","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6630","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"HI6ITF3Y635V","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HI6ITF3Y635V2HQQ","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HI6ITF3Y","created_at":"2026-05-18T12:28:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:HI6ITF3Y635V2HQQSYT5ZYCGPC","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6630","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T07:59:14Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"e0b953699d5d935fd14d0716e2d1ffe6a3f8b175896a7c38508902cb35bf7c2d","abstract_canon_sha256":"1cfc2bd3783fdffe3cc2c515d8dd4b38e6bd3fea478a498b4aa4db5424a4dd96"},"schema_version":"1.0"},"canonical_sha256":"3a3c899778f6fb5d1e109627dce04678b99e7a05699bd86c25118ca8db2f8b54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:07.592385Z","signature_b64":"/N55ytpD61SFu2HP9TY8xY8Bh1ldRLjE8YjXBn7a4nEzRtYi5/jibOQw0hrvWzZNl/UHXnfBT23hcrBi3t2hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a3c899778f6fb5d1e109627dce04678b99e7a05699bd86c25118ca8db2f8b54","last_reissued_at":"2026-05-18T02:30:07.591669Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:07.591669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6630","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":"2026-05-18T02:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5aO1sTSwtxoM5nqQ27AukLDGownrDLXHLcAfSez1GE/y7dohuB4Kdq8ZSdndgiJUGbnZYpH/dtg92QwtLG8EDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:59.961143Z"},"content_sha256":"5c0dcfe1c8f86ef4bfab7d16733cb3c69e530d4a4b8833306dcfb4ea5094ccef","schema_version":"1.0","event_id":"sha256:5c0dcfe1c8f86ef4bfab7d16733cb3c69e530d4a4b8833306dcfb4ea5094ccef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:HI6ITF3Y635V2HQQSYT5ZYCGPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Network Regularization via Robust Weight Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Jiwoong Im, Graham W. Taylor, Jan Rudy, Weiguang Ding","submitted_at":"2014-12-20T07:59:14Z","abstract_excerpt":"Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This results in poor generalization to unseen data. Therefore, it is no surprise that a new regularization technique, Dropout, was partially responsible for the now-ubiquitous winning entry to ImageNet 2012 by the University of Toronto. Currently, Dropout (and related methods such as DropConnect) are the most effective means of regularizing large neural networks. Thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6630","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":"2026-05-18T02:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNFN95tvxzuZ+gQ1fjO8oxoFSG5lKP3TDQdmSQUrkuVv3+tVjxa41bPu8tGML7tP731Sh0U3zvBaaYw/fqeIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:59.961517Z"},"content_sha256":"febbe66dc7387c7512942b70549b47d037940531aa9b7e61dff2cda2e685fd11","schema_version":"1.0","event_id":"sha256:febbe66dc7387c7512942b70549b47d037940531aa9b7e61dff2cda2e685fd11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/bundle.json","state_url":"https://pith.science/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/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":"2026-05-27T11:39:59Z","links":{"resolver":"https://pith.science/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC","bundle":"https://pith.science/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/bundle.json","state":"https://pith.science/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HI6ITF3Y635V2HQQSYT5ZYCGPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:HI6ITF3Y635V2HQQSYT5ZYCGPC","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":"1cfc2bd3783fdffe3cc2c515d8dd4b38e6bd3fea478a498b4aa4db5424a4dd96","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T07:59:14Z","title_canon_sha256":"e0b953699d5d935fd14d0716e2d1ffe6a3f8b175896a7c38508902cb35bf7c2d"},"schema_version":"1.0","source":{"id":"1412.6630","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6630","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6630v2","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6630","created_at":"2026-05-18T02:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"HI6ITF3Y635V","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HI6ITF3Y635V2HQQ","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HI6ITF3Y","created_at":"2026-05-18T12:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:febbe66dc7387c7512942b70549b47d037940531aa9b7e61dff2cda2e685fd11","target":"graph","created_at":"2026-05-18T02:30:07Z","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":"Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This results in poor generalization to unseen data. Therefore, it is no surprise that a new regularization technique, Dropout, was partially responsible for the now-ubiquitous winning entry to ImageNet 2012 by the University of Toronto. Currently, Dropout (and related methods such as DropConnect) are the most effective means of regularizing large neural networks. Thes","authors_text":"Daniel Jiwoong Im, Graham W. Taylor, Jan Rudy, Weiguang Ding","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T07:59:14Z","title":"Neural Network Regularization via Robust Weight Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6630","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":"sha256:5c0dcfe1c8f86ef4bfab7d16733cb3c69e530d4a4b8833306dcfb4ea5094ccef","target":"record","created_at":"2026-05-18T02:30:07Z","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":"1cfc2bd3783fdffe3cc2c515d8dd4b38e6bd3fea478a498b4aa4db5424a4dd96","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T07:59:14Z","title_canon_sha256":"e0b953699d5d935fd14d0716e2d1ffe6a3f8b175896a7c38508902cb35bf7c2d"},"schema_version":"1.0","source":{"id":"1412.6630","kind":"arxiv","version":2}},"canonical_sha256":"3a3c899778f6fb5d1e109627dce04678b99e7a05699bd86c25118ca8db2f8b54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a3c899778f6fb5d1e109627dce04678b99e7a05699bd86c25118ca8db2f8b54","first_computed_at":"2026-05-18T02:30:07.591669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:30:07.591669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/N55ytpD61SFu2HP9TY8xY8Bh1ldRLjE8YjXBn7a4nEzRtYi5/jibOQw0hrvWzZNl/UHXnfBT23hcrBi3t2hBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:30:07.592385Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6630","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c0dcfe1c8f86ef4bfab7d16733cb3c69e530d4a4b8833306dcfb4ea5094ccef","sha256:febbe66dc7387c7512942b70549b47d037940531aa9b7e61dff2cda2e685fd11"],"state_sha256":"4fdc566b46fe3417cf354752fc5b82700679a5e585fee5317043f5b42778a3fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTwq4AR6nF6fvNiu+HUqT0B3IWwEobGhsckJj6KYyD8YIDiVfoV4eMdACTVHBEkfDCr9tsPaqbYlGSLkjcIIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:39:59.963750Z","bundle_sha256":"8f79578577af16b77d5030b984b431e510e7495e490c180483781063fa8673a4"}}