{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:4QNKC4O7J57FMFS4OAQIVHLZ5G","short_pith_number":"pith:4QNKC4O7","schema_version":"1.0","canonical_sha256":"e41aa171df4f7e56165c70208a9d79e985cfce176b62bb42363353f76cb932e2","source":{"kind":"arxiv","id":"1409.2329","version":5},"attestation_state":"computed","paper":{"title":"Recurrent Neural Network Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Ilya Sutskever, Oriol Vinyals, Wojciech Zaremba","submitted_at":"2014-09-08T13:08:00Z","abstract_excerpt":"We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1409.2329","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-09-08T13:08:00Z","cross_cats_sorted":[],"title_canon_sha256":"cbed31a9b5a29742d077102c6082587aad80dfa5188b1e3104a14aafcd3e9871","abstract_canon_sha256":"e3435fadbeff7d28ca78fabfca33bdcced2231111f091fe681f2c1f4520b4fb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:51.483833Z","signature_b64":"AkmDgW2A7YP/HC9HOfhzE3sjXbCul0TZ+UZV2r+MmLip9LQpwGs+sxa17zDIYHa1k42NBkihDVQv57dA0G2DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e41aa171df4f7e56165c70208a9d79e985cfce176b62bb42363353f76cb932e2","last_reissued_at":"2026-05-18T02:26:51.482743Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:51.482743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Neural Network Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Ilya Sutskever, Oriol Vinyals, Wojciech Zaremba","submitted_at":"2014-09-08T13:08:00Z","abstract_excerpt":"We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.2329","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1409.2329","created_at":"2026-05-18T02:26:51.483436+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.2329v5","created_at":"2026-05-18T02:26:51.483436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.2329","created_at":"2026-05-18T02:26:51.483436+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QNKC4O7J57F","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QNKC4O7J57FMFS4","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QNKC4O7","created_at":"2026-05-18T12:28:14.216126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.08512","citing_title":"Adversarial Learning for Improved Onsets and Frames Music Transcription","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01470","citing_title":"Augmenting Self-attention with Persistent Memory","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04916","citing_title":"Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05720","citing_title":"Wind Estimation Using Quadcopter Motion: A Machine Learning Approach","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11064","citing_title":"Online Supervised Learning for Traffic Load Prediction in Framed-ALOHA Networks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06351","citing_title":"SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"1609.07843","citing_title":"Pointer Sentinel Mixture Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"1701.06538","citing_title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G","json":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G.json","graph_json":"https://pith.science/api/pith-number/4QNKC4O7J57FMFS4OAQIVHLZ5G/graph.json","events_json":"https://pith.science/api/pith-number/4QNKC4O7J57FMFS4OAQIVHLZ5G/events.json","paper":"https://pith.science/paper/4QNKC4O7"},"agent_actions":{"view_html":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G","download_json":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G.json","view_paper":"https://pith.science/paper/4QNKC4O7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.2329&json=true","fetch_graph":"https://pith.science/api/pith-number/4QNKC4O7J57FMFS4OAQIVHLZ5G/graph.json","fetch_events":"https://pith.science/api/pith-number/4QNKC4O7J57FMFS4OAQIVHLZ5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G/action/storage_attestation","attest_author":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G/action/author_attestation","sign_citation":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G/action/citation_signature","submit_replication":"https://pith.science/pith/4QNKC4O7J57FMFS4OAQIVHLZ5G/action/replication_record"}},"created_at":"2026-05-18T02:26:51.483436+00:00","updated_at":"2026-05-18T02:26:51.483436+00:00"}