{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:T33HH5DPVQDFID7OZZSVOW27TV","short_pith_number":"pith:T33HH5DP","canonical_record":{"source":{"id":"1808.03578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-10T15:06:05Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1d05fd5040a5e65bb2aea428434bcc7cc5de6a89cf04afbce9f10f24c6334314","abstract_canon_sha256":"2e387361ed5ac6256a6b4320b733bc6647a832dbc0f0c956e1edf6d8ef41711b"},"schema_version":"1.0"},"canonical_sha256":"9ef673f46fac06540feece65575b5f9d752aee0da8eaa86f7713d06add4907a0","source":{"kind":"arxiv","id":"1808.03578","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03578","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03578v2","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03578","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"T33HH5DPVQDF","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"T33HH5DPVQDFID7O","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"T33HH5DP","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:T33HH5DPVQDFID7OZZSVOW27TV","target":"record","payload":{"canonical_record":{"source":{"id":"1808.03578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-10T15:06:05Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1d05fd5040a5e65bb2aea428434bcc7cc5de6a89cf04afbce9f10f24c6334314","abstract_canon_sha256":"2e387361ed5ac6256a6b4320b733bc6647a832dbc0f0c956e1edf6d8ef41711b"},"schema_version":"1.0"},"canonical_sha256":"9ef673f46fac06540feece65575b5f9d752aee0da8eaa86f7713d06add4907a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:31.647026Z","signature_b64":"6hn4Ke2EDfRKjl+H6Iy1ZiqCCwjSFEUNn0sAd3rfsKBDl1H5jTnjgoO8Cz9R/9Lm9r5argmgieClTW8nRI15Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ef673f46fac06540feece65575b5f9d752aee0da8eaa86f7713d06add4907a0","last_reissued_at":"2026-05-17T23:54:31.646428Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:31.646428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.03578","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":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjDN7zMpNFqIfY1tIUZA3e98jgPWORP6wLGfM/b1ZQ9pFW37nhTk/OEBLSuMBcZ5T6edq7UNs+fTM6cUGUmAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:12:05.413123Z"},"content_sha256":"f714be2988947f7d4aab692bb5f3466f4ae3e0cad2de9857218f9004de3ad0ff","schema_version":"1.0","event_id":"sha256:f714be2988947f7d4aab692bb5f3466f4ae3e0cad2de9857218f9004de3ad0ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:T33HH5DPVQDFID7OZZSVOW27TV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout is a special case of the stochastic delta rule: faster and more accurate deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Noah Frazier-Logue, Stephen Jos\\'e Hanson","submitted_at":"2018-08-10T15:06:05Z","abstract_excerpt":"Multi-layer neural networks have lead to remarkable performance on many kinds of benchmark tasks in text, speech and image processing. Nonlinear parameter estimation in hierarchical models is known to be subject to overfitting and misspecification. One approach to these estimation and related problems (local minima, colinearity, feature discovery etc.) is called Dropout (Hinton, et al 2012, Baldi et al 2016). The Dropout algorithm removes hidden units according to a Bernoulli random variable with probability $p$ prior to each update, creating random \"shocks\" to the network that are averaged ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03578","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":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hyRgFAFCVpM7J0c21aUWbinQP15v7VhdPuy26+mxvPhN7kerzvyOSP4uupqSl4hFk/0EUKrefWEDHRo6rppQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:12:05.413838Z"},"content_sha256":"e49153e32e55954dd878e720b51c73499567c84afb7c98b0f2177784e976a8cf","schema_version":"1.0","event_id":"sha256:e49153e32e55954dd878e720b51c73499567c84afb7c98b0f2177784e976a8cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T33HH5DPVQDFID7OZZSVOW27TV/bundle.json","state_url":"https://pith.science/pith/T33HH5DPVQDFID7OZZSVOW27TV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T33HH5DPVQDFID7OZZSVOW27TV/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":"2026-05-25T23:12:05Z","links":{"resolver":"https://pith.science/pith/T33HH5DPVQDFID7OZZSVOW27TV","bundle":"https://pith.science/pith/T33HH5DPVQDFID7OZZSVOW27TV/bundle.json","state":"https://pith.science/pith/T33HH5DPVQDFID7OZZSVOW27TV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T33HH5DPVQDFID7OZZSVOW27TV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:T33HH5DPVQDFID7OZZSVOW27TV","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":"2e387361ed5ac6256a6b4320b733bc6647a832dbc0f0c956e1edf6d8ef41711b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-10T15:06:05Z","title_canon_sha256":"1d05fd5040a5e65bb2aea428434bcc7cc5de6a89cf04afbce9f10f24c6334314"},"schema_version":"1.0","source":{"id":"1808.03578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03578","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03578v2","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03578","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"T33HH5DPVQDF","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"T33HH5DPVQDFID7O","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"T33HH5DP","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:e49153e32e55954dd878e720b51c73499567c84afb7c98b0f2177784e976a8cf","target":"graph","created_at":"2026-05-17T23:54:31Z","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":"Multi-layer neural networks have lead to remarkable performance on many kinds of benchmark tasks in text, speech and image processing. Nonlinear parameter estimation in hierarchical models is known to be subject to overfitting and misspecification. One approach to these estimation and related problems (local minima, colinearity, feature discovery etc.) is called Dropout (Hinton, et al 2012, Baldi et al 2016). The Dropout algorithm removes hidden units according to a Bernoulli random variable with probability $p$ prior to each update, creating random \"shocks\" to the network that are averaged ov","authors_text":"Noah Frazier-Logue, Stephen Jos\\'e Hanson","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-10T15:06:05Z","title":"Dropout is a special case of the stochastic delta rule: faster and more accurate deep learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03578","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:f714be2988947f7d4aab692bb5f3466f4ae3e0cad2de9857218f9004de3ad0ff","target":"record","created_at":"2026-05-17T23:54:31Z","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":"2e387361ed5ac6256a6b4320b733bc6647a832dbc0f0c956e1edf6d8ef41711b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-10T15:06:05Z","title_canon_sha256":"1d05fd5040a5e65bb2aea428434bcc7cc5de6a89cf04afbce9f10f24c6334314"},"schema_version":"1.0","source":{"id":"1808.03578","kind":"arxiv","version":2}},"canonical_sha256":"9ef673f46fac06540feece65575b5f9d752aee0da8eaa86f7713d06add4907a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ef673f46fac06540feece65575b5f9d752aee0da8eaa86f7713d06add4907a0","first_computed_at":"2026-05-17T23:54:31.646428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:31.646428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6hn4Ke2EDfRKjl+H6Iy1ZiqCCwjSFEUNn0sAd3rfsKBDl1H5jTnjgoO8Cz9R/9Lm9r5argmgieClTW8nRI15Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:31.647026Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.03578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f714be2988947f7d4aab692bb5f3466f4ae3e0cad2de9857218f9004de3ad0ff","sha256:e49153e32e55954dd878e720b51c73499567c84afb7c98b0f2177784e976a8cf"],"state_sha256":"d3ca2d6acd8bff5b24e3fcf077f53e86d8712f5d632b66a1b67480bf158cd829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDxWAIc6VtbfNXStfHVxAPh+CNRQpRksghscLsMmvAkCsppgvV4hXufcVk0fDHagrm4sR/P9ktLoMJGWYvf8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:12:05.417775Z","bundle_sha256":"34c30b73b944d2c3c492e59831ff4df3a404641043b956eaafdf6655ddbea0cc"}}