{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NQ722SNIHLOFLHQWNDSWHCIJAO","short_pith_number":"pith:NQ722SNI","schema_version":"1.0","canonical_sha256":"6c3fad49a83adc559e1668e5638909039d25a9531b9ee0c0814fc164eab54392","source":{"kind":"arxiv","id":"1803.10225","version":1},"attestation_state":"computed","paper":{"title":"Light Gated Recurrent Units for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Maurizio Omologo, Mirco Ravanelli, Philemon Brakel, Yoshua Bengio","submitted_at":"2018-03-26T17:48:18Z","abstract_excerpt":"A field that has directly benefited from the recent advances in deep learning is Automatic Speech Recognition (ASR). Despite the great achievements of the past decades, however, a natural and robust human-machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on Recurrent Neural Networks (RNNs), that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to"},"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":"1803.10225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-03-26T17:48:18Z","cross_cats_sorted":["cs.NE","cs.SD","eess.SP"],"title_canon_sha256":"067ec2be18d19eb182395ceda065e969fa5c0811b8cef2c719613d9484e537f0","abstract_canon_sha256":"c7ba22bb31cfe006f406a943d14c848d2a772479bb16af453b84380c80267b14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.065543Z","signature_b64":"L2E5KwnFCv6VXJx/CYCp5TXRULb53tkKlq+9rQFhi76dL9WiHRyb0YW76rEogKQ88p/yqXEsxtzIW3YLPeXSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3fad49a83adc559e1668e5638909039d25a9531b9ee0c0814fc164eab54392","last_reissued_at":"2026-05-18T00:19:56.064921Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.064921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Light Gated Recurrent Units for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Maurizio Omologo, Mirco Ravanelli, Philemon Brakel, Yoshua Bengio","submitted_at":"2018-03-26T17:48:18Z","abstract_excerpt":"A field that has directly benefited from the recent advances in deep learning is Automatic Speech Recognition (ASR). Despite the great achievements of the past decades, however, a natural and robust human-machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on Recurrent Neural Networks (RNNs), that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10225","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":"1803.10225","created_at":"2026-05-18T00:19:56.065028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10225v1","created_at":"2026-05-18T00:19:56.065028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10225","created_at":"2026-05-18T00:19:56.065028+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQ722SNIHLOF","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQ722SNIHLOFLHQW","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQ722SNI","created_at":"2026-05-18T12:32:40.477152+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/NQ722SNIHLOFLHQWNDSWHCIJAO","json":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO.json","graph_json":"https://pith.science/api/pith-number/NQ722SNIHLOFLHQWNDSWHCIJAO/graph.json","events_json":"https://pith.science/api/pith-number/NQ722SNIHLOFLHQWNDSWHCIJAO/events.json","paper":"https://pith.science/paper/NQ722SNI"},"agent_actions":{"view_html":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO","download_json":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO.json","view_paper":"https://pith.science/paper/NQ722SNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10225&json=true","fetch_graph":"https://pith.science/api/pith-number/NQ722SNIHLOFLHQWNDSWHCIJAO/graph.json","fetch_events":"https://pith.science/api/pith-number/NQ722SNIHLOFLHQWNDSWHCIJAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO/action/storage_attestation","attest_author":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO/action/author_attestation","sign_citation":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO/action/citation_signature","submit_replication":"https://pith.science/pith/NQ722SNIHLOFLHQWNDSWHCIJAO/action/replication_record"}},"created_at":"2026-05-18T00:19:56.065028+00:00","updated_at":"2026-05-18T00:19:56.065028+00:00"}