{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GRDAEDAEE2PU4YD7IAGWHXXCRZ","short_pith_number":"pith:GRDAEDAE","schema_version":"1.0","canonical_sha256":"3446020c04269f4e607f400d63dee28e538b9c5a4979a6bde6094344952cd8ee","source":{"kind":"arxiv","id":"1607.03474","version":5},"attestation_state":"computed","paper":{"title":"Recurrent Highway Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jan Koutn\\'ik, Julian Georg Zilly, J\\\"urgen Schmidhuber, Rupesh Kumar Srivastava","submitted_at":"2016-07-12T19:36:50Z","abstract_excerpt":"Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with 'deep' transition functions remain difficult to train, even when using Long Short-Term Memory (LSTM) networks. We introduce a novel theoretical analysis of recurrent networks based on Gersgorin's circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell. Based on this analysis we propose Recurrent Highway Networks, which extend the LSTM architecture to allow step-to-step transition depth"},"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":"1607.03474","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-12T19:36:50Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"95afa9b1c8605f3e1bfa6366227f26ddd29935a02a20b08a1085f15440de3219","abstract_canon_sha256":"449d65d23e7a8d36e7541a328d76464b84f335e4ae07e1a456633491b3c1ce53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:54.055258Z","signature_b64":"oTUtjCXgL8iMkpXzzosp5HerLDd6DEMlW5lV27KkSEggCgT998LDaGi+alRxd0+TqG3hy6qTKN/ETTyVM9J4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3446020c04269f4e607f400d63dee28e538b9c5a4979a6bde6094344952cd8ee","last_reissued_at":"2026-05-18T00:40:54.054843Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:54.054843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Highway Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jan Koutn\\'ik, Julian Georg Zilly, J\\\"urgen Schmidhuber, Rupesh Kumar Srivastava","submitted_at":"2016-07-12T19:36:50Z","abstract_excerpt":"Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with 'deep' transition functions remain difficult to train, even when using Long Short-Term Memory (LSTM) networks. We introduce a novel theoretical analysis of recurrent networks based on Gersgorin's circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell. Based on this analysis we propose Recurrent Highway Networks, which extend the LSTM architecture to allow step-to-step transition depth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.03474","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":"1607.03474","created_at":"2026-05-18T00:40:54.054903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.03474v5","created_at":"2026-05-18T00:40:54.054903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.03474","created_at":"2026-05-18T00:40:54.054903+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRDAEDAEE2PU","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRDAEDAEE2PU4YD7","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRDAEDAE","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1609.07843","citing_title":"Pointer Sentinel Mixture Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2308.00352","citing_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ","json":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ.json","graph_json":"https://pith.science/api/pith-number/GRDAEDAEE2PU4YD7IAGWHXXCRZ/graph.json","events_json":"https://pith.science/api/pith-number/GRDAEDAEE2PU4YD7IAGWHXXCRZ/events.json","paper":"https://pith.science/paper/GRDAEDAE"},"agent_actions":{"view_html":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ","download_json":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ.json","view_paper":"https://pith.science/paper/GRDAEDAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.03474&json=true","fetch_graph":"https://pith.science/api/pith-number/GRDAEDAEE2PU4YD7IAGWHXXCRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GRDAEDAEE2PU4YD7IAGWHXXCRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ/action/storage_attestation","attest_author":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ/action/author_attestation","sign_citation":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ/action/citation_signature","submit_replication":"https://pith.science/pith/GRDAEDAEE2PU4YD7IAGWHXXCRZ/action/replication_record"}},"created_at":"2026-05-18T00:40:54.054903+00:00","updated_at":"2026-05-18T00:40:54.054903+00:00"}