{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:JW64SOLDVWNVSCBAN3LGJR4EEH","short_pith_number":"pith:JW64SOLD","canonical_record":{"source":{"id":"1512.05287","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-16T19:18:43Z","cross_cats_sorted":[],"title_canon_sha256":"670df0862091ec7a01f91d09c66fba77b30ed07188cc13af484d57e2aed0b39d","abstract_canon_sha256":"85e4d1c0c0e0965505ea81a1aab6c8d78fc53fb5ac09cfecc1d17b67c1016bff"},"schema_version":"1.0"},"canonical_sha256":"4dbdc93963ad9b5908206ed664c78421cad9e3ca777526e56bfef3ea3562be5e","source":{"kind":"arxiv","id":"1512.05287","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.05287","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"1512.05287v5","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05287","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"JW64SOLDVWNV","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JW64SOLDVWNVSCBA","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JW64SOLD","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:JW64SOLDVWNVSCBAN3LGJR4EEH","target":"record","payload":{"canonical_record":{"source":{"id":"1512.05287","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-16T19:18:43Z","cross_cats_sorted":[],"title_canon_sha256":"670df0862091ec7a01f91d09c66fba77b30ed07188cc13af484d57e2aed0b39d","abstract_canon_sha256":"85e4d1c0c0e0965505ea81a1aab6c8d78fc53fb5ac09cfecc1d17b67c1016bff"},"schema_version":"1.0"},"canonical_sha256":"4dbdc93963ad9b5908206ed664c78421cad9e3ca777526e56bfef3ea3562be5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:10.728421Z","signature_b64":"q4n10TEzEMEYgHvdNoyR6HrmLDgjwJogFUy5of34eYnmRxoB0DYwkl5cvaklmtwIhTlmWlYkmyw9A8AKfSrIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dbdc93963ad9b5908206ed664c78421cad9e3ca777526e56bfef3ea3562be5e","last_reissued_at":"2026-05-18T01:03:10.727753Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:10.727753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.05287","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFtBZdCfarkfo3cS1rISPXgCSG5lazhhr0glG55clTf3PEc8jpk44VDYgSm7Vw0R6uHmoIkJLbMwpWa1glJWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:21:35.445496Z"},"content_sha256":"e1db63d8a2dc21c47e8d0978b5e02422b96c2e941f7d368a88c805c873e48d18","schema_version":"1.0","event_id":"sha256:e1db63d8a2dc21c47e8d0978b5e02422b96c2e941f7d368a88c805c873e48d18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:JW64SOLDVWNVSCBAN3LGJR4EEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Yarin Gal, Zoubin Ghahramani","submitted_at":"2015-12-16T19:18:43Z","abstract_excerpt":"Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout. This grounding of dropout in approximate Bayesian inference suggests an extension of the theoretical results, offering insights into the use of dropout with RNN models. We apply this new variational inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05287","kind":"arxiv","version":5},"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":"2026-05-18T01:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7eE4WBBuiy2aOSOvTDLTxZtX6PSHLS7PBePry2dcov90paM/3Na3upWCy9AYg9ZR6YzhQ1gVybWSReliNjJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:21:35.445845Z"},"content_sha256":"4967a914de9f970c4aee4de7fc657625c4137188c9ae14db624303561204835e","schema_version":"1.0","event_id":"sha256:4967a914de9f970c4aee4de7fc657625c4137188c9ae14db624303561204835e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/bundle.json","state_url":"https://pith.science/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/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":"2026-05-28T05:21:35Z","links":{"resolver":"https://pith.science/pith/JW64SOLDVWNVSCBAN3LGJR4EEH","bundle":"https://pith.science/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/bundle.json","state":"https://pith.science/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW64SOLDVWNVSCBAN3LGJR4EEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:JW64SOLDVWNVSCBAN3LGJR4EEH","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":"85e4d1c0c0e0965505ea81a1aab6c8d78fc53fb5ac09cfecc1d17b67c1016bff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-16T19:18:43Z","title_canon_sha256":"670df0862091ec7a01f91d09c66fba77b30ed07188cc13af484d57e2aed0b39d"},"schema_version":"1.0","source":{"id":"1512.05287","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.05287","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"1512.05287v5","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05287","created_at":"2026-05-18T01:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"JW64SOLDVWNV","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JW64SOLDVWNVSCBA","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JW64SOLD","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:4967a914de9f970c4aee4de7fc657625c4137188c9ae14db624303561204835e","target":"graph","created_at":"2026-05-18T01:03:10Z","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":"Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout. This grounding of dropout in approximate Bayesian inference suggests an extension of the theoretical results, offering insights into the use of dropout with RNN models. We apply this new variational inferenc","authors_text":"Yarin Gal, Zoubin Ghahramani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-16T19:18:43Z","title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05287","kind":"arxiv","version":5},"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:e1db63d8a2dc21c47e8d0978b5e02422b96c2e941f7d368a88c805c873e48d18","target":"record","created_at":"2026-05-18T01:03:10Z","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":"85e4d1c0c0e0965505ea81a1aab6c8d78fc53fb5ac09cfecc1d17b67c1016bff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-16T19:18:43Z","title_canon_sha256":"670df0862091ec7a01f91d09c66fba77b30ed07188cc13af484d57e2aed0b39d"},"schema_version":"1.0","source":{"id":"1512.05287","kind":"arxiv","version":5}},"canonical_sha256":"4dbdc93963ad9b5908206ed664c78421cad9e3ca777526e56bfef3ea3562be5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dbdc93963ad9b5908206ed664c78421cad9e3ca777526e56bfef3ea3562be5e","first_computed_at":"2026-05-18T01:03:10.727753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:10.727753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4n10TEzEMEYgHvdNoyR6HrmLDgjwJogFUy5of34eYnmRxoB0DYwkl5cvaklmtwIhTlmWlYkmyw9A8AKfSrIAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:10.728421Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.05287","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1db63d8a2dc21c47e8d0978b5e02422b96c2e941f7d368a88c805c873e48d18","sha256:4967a914de9f970c4aee4de7fc657625c4137188c9ae14db624303561204835e"],"state_sha256":"8c8158ba52003eddf3cf5713820b7312b4eaf11a7597cf1612fec5b9cc283180"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3cMiYja8PFe6MGsOP3GWApHfHV/yTkHC88ETr6hftJOSC2rDvpxu11/Cs1C/Pn70ilINvismNKThS3cw+cB9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T05:21:35.447822Z","bundle_sha256":"caf1c6ec075aa6a87c8f2b00a4aec2b50cf1c8d054b7ba091aff68c7cb321247"}}