{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TSE6BMATFUD3POPIOJIMDZ2CNC","short_pith_number":"pith:TSE6BMAT","schema_version":"1.0","canonical_sha256":"9c89e0b0132d07b7b9e87250c1e742688ef2fd629e1138fb7babe8982a4753fd","source":{"kind":"arxiv","id":"1503.04069","version":2},"attestation_state":"computed","paper":{"title":"LSTM: A Search Space Odyssey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Bas R. Steunebrink, Jan Koutn\\'ik, J\\\"urgen Schmidhuber, Klaus Greff, Rupesh Kumar Srivastava","submitted_at":"2015-03-13T14:01:38Z","abstract_excerpt":"Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparamete"},"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":"1503.04069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-03-13T14:01:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"310adfa63b0f1408ca1b4acf2af9c55ea3edfca690210be40a43999571eb4708","abstract_canon_sha256":"4438658bee04b4c40a0def0f37c1f02ec691ee7a19463704366ac58d6b6c5bd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:44.322579Z","signature_b64":"2DDJWGt3fVheSB8PRujD5b4ook91ge81PdsO73JEKrsjiAoeZPHk6A2gt6U6Fv2wr3aaAQ25CSoTo4O1axnPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c89e0b0132d07b7b9e87250c1e742688ef2fd629e1138fb7babe8982a4753fd","last_reissued_at":"2026-05-18T00:33:44.322000Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:44.322000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSTM: A Search Space Odyssey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Bas R. Steunebrink, Jan Koutn\\'ik, J\\\"urgen Schmidhuber, Klaus Greff, Rupesh Kumar Srivastava","submitted_at":"2015-03-13T14:01:38Z","abstract_excerpt":"Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparamete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04069","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.04069","created_at":"2026-05-18T00:33:44.322095+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.04069v2","created_at":"2026-05-18T00:33:44.322095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04069","created_at":"2026-05-18T00:33:44.322095+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSE6BMATFUD3","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSE6BMATFUD3POPI","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSE6BMAT","created_at":"2026-05-18T12:29:42.218222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":209,"is_internal_anchor":true},{"citing_arxiv_id":"2308.00352","citing_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","ref_index":145,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC","json":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC.json","graph_json":"https://pith.science/api/pith-number/TSE6BMATFUD3POPIOJIMDZ2CNC/graph.json","events_json":"https://pith.science/api/pith-number/TSE6BMATFUD3POPIOJIMDZ2CNC/events.json","paper":"https://pith.science/paper/TSE6BMAT"},"agent_actions":{"view_html":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC","download_json":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC.json","view_paper":"https://pith.science/paper/TSE6BMAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.04069&json=true","fetch_graph":"https://pith.science/api/pith-number/TSE6BMATFUD3POPIOJIMDZ2CNC/graph.json","fetch_events":"https://pith.science/api/pith-number/TSE6BMATFUD3POPIOJIMDZ2CNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC/action/storage_attestation","attest_author":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC/action/author_attestation","sign_citation":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC/action/citation_signature","submit_replication":"https://pith.science/pith/TSE6BMATFUD3POPIOJIMDZ2CNC/action/replication_record"}},"created_at":"2026-05-18T00:33:44.322095+00:00","updated_at":"2026-05-18T00:33:44.322095+00:00"}