{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6SBUATM7PHFQJWSTXVQYURVU5V","short_pith_number":"pith:6SBUATM7","schema_version":"1.0","canonical_sha256":"f483404d9f79cb04da53bd618a46b4ed65b5293c2f0068b2f0b850e50942bc90","source":{"kind":"arxiv","id":"1709.06436","version":1},"attestation_state":"computed","paper":{"title":"Language Modeling with Highway LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhinav Sethy, Bhuvana Ramabhadran, Gakuto Kurata, George Saon","submitted_at":"2017-09-19T14:04:15Z","abstract_excerpt":"Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM (HW-LSTM) model for language modeling. The added highway networks increase the depth in the time dimension. Since a typical LSTM has two internal states, a memory cell and a hidden state, we compare various types of HW-LSTM by adding highway networks onto the memory cell and/or the hidden state. Experimental results on English broadcast news and conversational "},"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":"1709.06436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T14:04:15Z","cross_cats_sorted":[],"title_canon_sha256":"1e4f2c06798ee3e7afdb091adf4ada908a58864ca00c18c32f3722cc05ae4028","abstract_canon_sha256":"5f25c2f7f6d8a507f8eb2e7dd487d0e10d9c15ed8496cd8b73e2b15775ce8740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:45.836008Z","signature_b64":"B8Goag6Ssc0/gXd3oh69jVeIqhJTan9HtGwq0fHJZ4nDKL2RDc+F+7felTmvTkYa4IIgFrJIZnj+o1/2OU1vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f483404d9f79cb04da53bd618a46b4ed65b5293c2f0068b2f0b850e50942bc90","last_reissued_at":"2026-05-18T00:34:45.835251Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:45.835251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Modeling with Highway LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhinav Sethy, Bhuvana Ramabhadran, Gakuto Kurata, George Saon","submitted_at":"2017-09-19T14:04:15Z","abstract_excerpt":"Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM (HW-LSTM) model for language modeling. The added highway networks increase the depth in the time dimension. Since a typical LSTM has two internal states, a memory cell and a hidden state, we compare various types of HW-LSTM by adding highway networks onto the memory cell and/or the hidden state. Experimental results on English broadcast news and conversational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06436","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":""},"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":"1709.06436","created_at":"2026-05-18T00:34:45.835380+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06436v1","created_at":"2026-05-18T00:34:45.835380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06436","created_at":"2026-05-18T00:34:45.835380+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SBUATM7PHFQ","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SBUATM7PHFQJWST","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SBUATM7","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V","json":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V.json","graph_json":"https://pith.science/api/pith-number/6SBUATM7PHFQJWSTXVQYURVU5V/graph.json","events_json":"https://pith.science/api/pith-number/6SBUATM7PHFQJWSTXVQYURVU5V/events.json","paper":"https://pith.science/paper/6SBUATM7"},"agent_actions":{"view_html":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V","download_json":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V.json","view_paper":"https://pith.science/paper/6SBUATM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06436&json=true","fetch_graph":"https://pith.science/api/pith-number/6SBUATM7PHFQJWSTXVQYURVU5V/graph.json","fetch_events":"https://pith.science/api/pith-number/6SBUATM7PHFQJWSTXVQYURVU5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V/action/storage_attestation","attest_author":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V/action/author_attestation","sign_citation":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V/action/citation_signature","submit_replication":"https://pith.science/pith/6SBUATM7PHFQJWSTXVQYURVU5V/action/replication_record"}},"created_at":"2026-05-18T00:34:45.835380+00:00","updated_at":"2026-05-18T00:34:45.835380+00:00"}