{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C5L6G4HGMXNSEV5OPGO2BPF3FB","short_pith_number":"pith:C5L6G4HG","schema_version":"1.0","canonical_sha256":"1757e370e665db2257ae799da0bcbb28632afdc3052c5db8155d3336fcd8789a","source":{"kind":"arxiv","id":"1909.09586","version":1},"attestation_state":"computed","paper":{"title":"Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Eric Rothstein Morris, Ralf C. Staudemeyer","submitted_at":"2019-09-12T15:44:51Z","abstract_excerpt":"Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) are one of the most powerful dynamic classifiers publicly known. The network itself and the related learning algorithms are reasonably well documented to get an idea how it works. This paper will shed more light into understanding how LSTM-RNNs evolved and why they work impressively well, focusing on the early, ground-breaking publications. We significantly improved documentation and fixed a number of errors and inconsistencies that accumulated in previous publications. To support understanding we as well revised and unified the notat"},"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":"1909.09586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-09-12T15:44:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d930ee4f27dccd0fdcce6b30a59d5679a64f883d3539ca96a950cb9f7fc8d9ee","abstract_canon_sha256":"3a1ee6360f5fdf2f4e0c5da90f61c0f994faf45ed19dc3590566e6117cc09032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:01.920363Z","signature_b64":"8g+CJI06dew0gzNieMm+GEZq3xtFxLh/31c5GUvFMi8Y/bXFTgGS7KRYcTSUmyRx1HrmNDCqCpWSEGtD6hIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1757e370e665db2257ae799da0bcbb28632afdc3052c5db8155d3336fcd8789a","last_reissued_at":"2026-07-05T00:06:01.919883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:01.919883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Eric Rothstein Morris, Ralf C. Staudemeyer","submitted_at":"2019-09-12T15:44:51Z","abstract_excerpt":"Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) are one of the most powerful dynamic classifiers publicly known. The network itself and the related learning algorithms are reasonably well documented to get an idea how it works. This paper will shed more light into understanding how LSTM-RNNs evolved and why they work impressively well, focusing on the early, ground-breaking publications. We significantly improved documentation and fixed a number of errors and inconsistencies that accumulated in previous publications. To support understanding we as well revised and unified the notat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09586","kind":"arxiv","version":1},"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/1909.09586/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":"1909.09586","created_at":"2026-07-05T00:06:01.919939+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09586v1","created_at":"2026-07-05T00:06:01.919939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09586","created_at":"2026-07-05T00:06:01.919939+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5L6G4HGMXNS","created_at":"2026-07-05T00:06:01.919939+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5L6G4HGMXNSEV5O","created_at":"2026-07-05T00:06:01.919939+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5L6G4HG","created_at":"2026-07-05T00:06:01.919939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19139","citing_title":"Urdu Katib Handwritten Dataset: A Historical Document Dataset for Offline Urdu Handwritten Text Recognition with CRNN-Based Baseline Evaluation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14855","citing_title":"Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27299","citing_title":"Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20192","citing_title":"Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.18177","citing_title":"Differential-UMamba: Rethinking Tumor Segmentation Under Limited Data Scenarios","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12898","citing_title":"BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB","json":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB.json","graph_json":"https://pith.science/api/pith-number/C5L6G4HGMXNSEV5OPGO2BPF3FB/graph.json","events_json":"https://pith.science/api/pith-number/C5L6G4HGMXNSEV5OPGO2BPF3FB/events.json","paper":"https://pith.science/paper/C5L6G4HG"},"agent_actions":{"view_html":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB","download_json":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB.json","view_paper":"https://pith.science/paper/C5L6G4HG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09586&json=true","fetch_graph":"https://pith.science/api/pith-number/C5L6G4HGMXNSEV5OPGO2BPF3FB/graph.json","fetch_events":"https://pith.science/api/pith-number/C5L6G4HGMXNSEV5OPGO2BPF3FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB/action/storage_attestation","attest_author":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB/action/author_attestation","sign_citation":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB/action/citation_signature","submit_replication":"https://pith.science/pith/C5L6G4HGMXNSEV5OPGO2BPF3FB/action/replication_record"}},"created_at":"2026-07-05T00:06:01.919939+00:00","updated_at":"2026-07-05T00:06:01.919939+00:00"}