{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IARKCEDE5QU4TSPIWA5YWSMWW5","short_pith_number":"pith:IARKCEDE","canonical_record":{"source":{"id":"1805.01500","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-03T18:34:52Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"deb1f71f28db351a9ad1d3cdd454f47fb077473f324049192a6ce53e44bf4b4c","abstract_canon_sha256":"0279661ce2a9fcffc1e8bf2a64d7a80b937c7e59377a87785818365bae5af142"},"schema_version":"1.0"},"canonical_sha256":"4022a11064ec29c9c9e8b03b8b4996b74d0cd31dc43565dee7910702c7bb8ade","source":{"kind":"arxiv","id":"1805.01500","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01500","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01500v2","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01500","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"IARKCEDE5QU4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IARKCEDE5QU4TSPI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IARKCEDE","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IARKCEDE5QU4TSPIWA5YWSMWW5","target":"record","payload":{"canonical_record":{"source":{"id":"1805.01500","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-03T18:34:52Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"deb1f71f28db351a9ad1d3cdd454f47fb077473f324049192a6ce53e44bf4b4c","abstract_canon_sha256":"0279661ce2a9fcffc1e8bf2a64d7a80b937c7e59377a87785818365bae5af142"},"schema_version":"1.0"},"canonical_sha256":"4022a11064ec29c9c9e8b03b8b4996b74d0cd31dc43565dee7910702c7bb8ade","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:51.812016Z","signature_b64":"gqsLyYpwDgEgTanJY95Fyb4vV0PQ8T1H0OXzyQ3RMCPtPDytl/clYZGwEngEmjfX/9aHeFvM2Jd7YIFsErN3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4022a11064ec29c9c9e8b03b8b4996b74d0cd31dc43565dee7910702c7bb8ade","last_reissued_at":"2026-05-18T00:10:51.811599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:51.811599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.01500","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":"2026-05-18T00:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDA1wAh6aG79MqDenqBn8HJv0Ij9qpaGSzryyPqpobN5RSDAwdmVgsuWPg01HGjzffAKwYCd62uKNNgoHENKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:20:33.429415Z"},"content_sha256":"7ed1cbd076cc2413f313330458384ea8fd71ec5c172055d97f3718874dc5bfd0","schema_version":"1.0","event_id":"sha256:7ed1cbd076cc2413f313330458384ea8fd71ec5c172055d97f3718874dc5bfd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IARKCEDE5QU4TSPIWA5YWSMWW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noisin: Unbiased Regularization for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Adji B. Dieng, David M. Blei, Jaan Altosaar, Rajesh Ranganath","submitted_at":"2018-05-03T18:34:52Z","abstract_excerpt":"Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we develop Noisin, a new method for regularizing RNNs. Noisin injects random noise into the hidden states of the RNN and then maximizes the corresponding marginal likelihood of the data. We show how Noisin applies to any RNN and we study many different types of noise. Noisin is unbiased--it preserves the underlying RNN on average. We characterize how Noisin regulariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01500","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":"2026-05-18T00:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8GY9obzX9hHcTCDViPR4GsFgn279XpuCzEMcSwXjSNbUZs3MBwGgl9WVyQmrTFcu5Hlf+JFra8go33CkKuKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:20:33.429766Z"},"content_sha256":"a2bdd05456a9553697e77af6b446524d358f861e2491cb358fddf6047cd8bc54","schema_version":"1.0","event_id":"sha256:a2bdd05456a9553697e77af6b446524d358f861e2491cb358fddf6047cd8bc54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/bundle.json","state_url":"https://pith.science/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/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":"2026-06-01T20:20:33Z","links":{"resolver":"https://pith.science/pith/IARKCEDE5QU4TSPIWA5YWSMWW5","bundle":"https://pith.science/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/bundle.json","state":"https://pith.science/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IARKCEDE5QU4TSPIWA5YWSMWW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IARKCEDE5QU4TSPIWA5YWSMWW5","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":"0279661ce2a9fcffc1e8bf2a64d7a80b937c7e59377a87785818365bae5af142","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-03T18:34:52Z","title_canon_sha256":"deb1f71f28db351a9ad1d3cdd454f47fb077473f324049192a6ce53e44bf4b4c"},"schema_version":"1.0","source":{"id":"1805.01500","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01500","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01500v2","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01500","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"IARKCEDE5QU4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IARKCEDE5QU4TSPI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IARKCEDE","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:a2bdd05456a9553697e77af6b446524d358f861e2491cb358fddf6047cd8bc54","target":"graph","created_at":"2026-05-18T00:10:51Z","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) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we develop Noisin, a new method for regularizing RNNs. Noisin injects random noise into the hidden states of the RNN and then maximizes the corresponding marginal likelihood of the data. We show how Noisin applies to any RNN and we study many different types of noise. Noisin is unbiased--it preserves the underlying RNN on average. We characterize how Noisin regulariz","authors_text":"Adji B. Dieng, David M. Blei, Jaan Altosaar, Rajesh Ranganath","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-03T18:34:52Z","title":"Noisin: Unbiased Regularization for Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01500","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":"sha256:7ed1cbd076cc2413f313330458384ea8fd71ec5c172055d97f3718874dc5bfd0","target":"record","created_at":"2026-05-18T00:10:51Z","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":"0279661ce2a9fcffc1e8bf2a64d7a80b937c7e59377a87785818365bae5af142","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-03T18:34:52Z","title_canon_sha256":"deb1f71f28db351a9ad1d3cdd454f47fb077473f324049192a6ce53e44bf4b4c"},"schema_version":"1.0","source":{"id":"1805.01500","kind":"arxiv","version":2}},"canonical_sha256":"4022a11064ec29c9c9e8b03b8b4996b74d0cd31dc43565dee7910702c7bb8ade","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4022a11064ec29c9c9e8b03b8b4996b74d0cd31dc43565dee7910702c7bb8ade","first_computed_at":"2026-05-18T00:10:51.811599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:51.811599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqsLyYpwDgEgTanJY95Fyb4vV0PQ8T1H0OXzyQ3RMCPtPDytl/clYZGwEngEmjfX/9aHeFvM2Jd7YIFsErN3BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:51.812016Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.01500","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ed1cbd076cc2413f313330458384ea8fd71ec5c172055d97f3718874dc5bfd0","sha256:a2bdd05456a9553697e77af6b446524d358f861e2491cb358fddf6047cd8bc54"],"state_sha256":"8289088d0d4702ea166f1827af4ad10957802d1b94f9672d6b9073abb03579e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gOTUdhBwq0ATt1Bx13/YRVMESStWFL1T1zuKfyYxT38ujdQ5HxJHKZUw9hCiBBgcDvSj4v20J8qMcZYfFQbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:20:33.431774Z","bundle_sha256":"1f4b19fdb02cd3707dfd35973aa3346f4222aa0be36de81d486d501b4015085e"}}