{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HLE6RBU4SZKMZFFF2LNPZE4ZTZ","short_pith_number":"pith:HLE6RBU4","schema_version":"1.0","canonical_sha256":"3ac9e8869c9654cc94a5d2dafc93999e5b86391c53c61a6e3ac1ad3c98cabbe2","source":{"kind":"arxiv","id":"1710.00641","version":1},"attestation_state":"computed","paper":{"title":"Improving speech recognition by revising gated recurrent units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Maurizio Omologo, Mirco Ravanelli, Philemon Brakel, Yoshua Bengio","submitted_at":"2017-09-29T12:40:50Z","abstract_excerpt":"Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach state-of-the-art performance in many tasks thanks to their ability to learn long-term dependencies and robustness to vanishing gradients. Nevertheless, LSTMs have a rather complex design with three multiplicative gates, that might impair their efficient implementation. An attempt to simplify LSTMs has recently led to Gated Recurrent Units (GRUs), which are ba"},"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":"1710.00641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-29T12:40:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"c65945946150b29cb817fab0ff5c6f72520796671c0f7e2e7dcd2f0ae2150d9a","abstract_canon_sha256":"90079b3e21296e1800bd7a2eef1cef1aa71abbbb1e1e45a36b5cd3f2b3d00efd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:54.149010Z","signature_b64":"0eBWkxzHac1KuYHA8LzryouRneXH1TdWr0Q8/qUBYL9rv47UKFnph9hRnCHRviYfvF+8x2yek212GNHyMoG9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac9e8869c9654cc94a5d2dafc93999e5b86391c53c61a6e3ac1ad3c98cabbe2","last_reissued_at":"2026-05-18T00:33:54.148457Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:54.148457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving speech recognition by revising gated recurrent units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Maurizio Omologo, Mirco Ravanelli, Philemon Brakel, Yoshua Bengio","submitted_at":"2017-09-29T12:40:50Z","abstract_excerpt":"Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach state-of-the-art performance in many tasks thanks to their ability to learn long-term dependencies and robustness to vanishing gradients. Nevertheless, LSTMs have a rather complex design with three multiplicative gates, that might impair their efficient implementation. An attempt to simplify LSTMs has recently led to Gated Recurrent Units (GRUs), which are ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00641","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":"1710.00641","created_at":"2026-05-18T00:33:54.148550+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.00641v1","created_at":"2026-05-18T00:33:54.148550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00641","created_at":"2026-05-18T00:33:54.148550+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLE6RBU4SZKM","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLE6RBU4SZKMZFFF","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLE6RBU4","created_at":"2026-05-18T12:31:18.294218+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/HLE6RBU4SZKMZFFF2LNPZE4ZTZ","json":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ.json","graph_json":"https://pith.science/api/pith-number/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/graph.json","events_json":"https://pith.science/api/pith-number/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/events.json","paper":"https://pith.science/paper/HLE6RBU4"},"agent_actions":{"view_html":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ","download_json":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ.json","view_paper":"https://pith.science/paper/HLE6RBU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.00641&json=true","fetch_graph":"https://pith.science/api/pith-number/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/action/storage_attestation","attest_author":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/action/author_attestation","sign_citation":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/action/citation_signature","submit_replication":"https://pith.science/pith/HLE6RBU4SZKMZFFF2LNPZE4ZTZ/action/replication_record"}},"created_at":"2026-05-18T00:33:54.148550+00:00","updated_at":"2026-05-18T00:33:54.148550+00:00"}