{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VLICS6EXAI3LJ7T3EJHMNJXSO6","short_pith_number":"pith:VLICS6EX","schema_version":"1.0","canonical_sha256":"aad02978970236b4fe7b224ec6a6f2778a347e69a8820ec6458c191797fc5859","source":{"kind":"arxiv","id":"1808.03314","version":10},"attestation_state":"computed","paper":{"title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Sherstinsky","submitted_at":"2018-08-09T19:31:42Z","abstract_excerpt":"Because of their effectiveness in broad practical applications, LSTM networks have received a wealth of coverage in scientific journals, technical blogs, and implementation guides. However, in most articles, the inference formulas for the LSTM network and its parent, RNN, are stated axiomatically, while the training formulas are omitted altogether. In addition, the technique of \"unrolling\" an RNN is routinely presented without justification throughout the literature. The goal of this paper is to explain the essential RNN and LSTM fundamentals in a single document. Drawing from concepts in sign"},"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":"1808.03314","kind":"arxiv","version":10},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-09T19:31:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"78dcaa7f2154b88fa94ac4034ba33efcafe44cf9abf18a70fab302a3847e0fa6","abstract_canon_sha256":"faa6f32542459b1ac36e093e94d76d8c7b69add1fcbe73ea5fc72c35ce4cc3ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:40.700186Z","signature_b64":"+vFe7PC7WlofFAGpLncIzesZM0pTYOyVu/oqEeEZnSH+KWDjTqRS8etCgpcZeKuWOhfIye0HehfqdMp7tn2OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad02978970236b4fe7b224ec6a6f2778a347e69a8820ec6458c191797fc5859","last_reissued_at":"2026-07-05T06:35:40.699679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:40.699679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Sherstinsky","submitted_at":"2018-08-09T19:31:42Z","abstract_excerpt":"Because of their effectiveness in broad practical applications, LSTM networks have received a wealth of coverage in scientific journals, technical blogs, and implementation guides. However, in most articles, the inference formulas for the LSTM network and its parent, RNN, are stated axiomatically, while the training formulas are omitted altogether. In addition, the technique of \"unrolling\" an RNN is routinely presented without justification throughout the literature. The goal of this paper is to explain the essential RNN and LSTM fundamentals in a single document. Drawing from concepts in sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03314","kind":"arxiv","version":10},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1808.03314/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1808.03314","created_at":"2026-07-05T06:35:40.699737+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03314v10","created_at":"2026-07-05T06:35:40.699737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03314","created_at":"2026-07-05T06:35:40.699737+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLICS6EXAI3L","created_at":"2026-07-05T06:35:40.699737+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLICS6EXAI3LJ7T3","created_at":"2026-07-05T06:35:40.699737+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLICS6EX","created_at":"2026-07-05T06:35:40.699737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17461","citing_title":"Electroweak diboson production in association with a high-mass dijet system in semileptonic final states from $pp$ collisions at $\\sqrt{s} = 13$ TeV with the ATLAS detector","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6","json":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6.json","graph_json":"https://pith.science/api/pith-number/VLICS6EXAI3LJ7T3EJHMNJXSO6/graph.json","events_json":"https://pith.science/api/pith-number/VLICS6EXAI3LJ7T3EJHMNJXSO6/events.json","paper":"https://pith.science/paper/VLICS6EX"},"agent_actions":{"view_html":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6","download_json":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6.json","view_paper":"https://pith.science/paper/VLICS6EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03314&json=true","fetch_graph":"https://pith.science/api/pith-number/VLICS6EXAI3LJ7T3EJHMNJXSO6/graph.json","fetch_events":"https://pith.science/api/pith-number/VLICS6EXAI3LJ7T3EJHMNJXSO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6/action/storage_attestation","attest_author":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6/action/author_attestation","sign_citation":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6/action/citation_signature","submit_replication":"https://pith.science/pith/VLICS6EXAI3LJ7T3EJHMNJXSO6/action/replication_record"}},"created_at":"2026-07-05T06:35:40.699737+00:00","updated_at":"2026-07-05T06:35:40.699737+00:00"}