{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YUWYWMRBE5NVOBFZVUORRCPVK4","short_pith_number":"pith:YUWYWMRB","schema_version":"1.0","canonical_sha256":"c52d8b3221275b5704b9ad1d1889f5573a546e120d353a7a83ef2c0497bc7840","source":{"kind":"arxiv","id":"1808.01916","version":1},"attestation_state":"computed","paper":{"title":"Residual Memory Networks: Feed-forward approach to learn long temporal dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Frantisek Grezl, Jan Honza Cernocky, Karel Vesely, Lukas Burget, Martin Karafiat, Murali Karthick Baskar","submitted_at":"2018-08-06T14:00:40Z","abstract_excerpt":"Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not possible. In this paper we propose a residual memory neural network (RMN) architecture to model short-time dependencies using deep feed-forward layers having residual and time delayed connections. The residual connection paves way to construct deeper networks by enabling unhindered f"},"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":"1808.01916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-06T14:00:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b9820c0a74257545610d77964c5dbd32cdf34c491f98814de7937dc4544ed2f9","abstract_canon_sha256":"fe610b50efde7dbe95c7fd0a14ff36390e420a5298b03da8878366265934399d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:49.223733Z","signature_b64":"KpE5vngHMedTFqjUsOb3M12pxB254fXIrqv0MbAut/EdgMTNknDqjTDkYeAZMF55wTNWbnFDBGUqeZuzkp+OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c52d8b3221275b5704b9ad1d1889f5573a546e120d353a7a83ef2c0497bc7840","last_reissued_at":"2026-05-18T00:08:49.223095Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:49.223095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Memory Networks: Feed-forward approach to learn long temporal dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Frantisek Grezl, Jan Honza Cernocky, Karel Vesely, Lukas Burget, Martin Karafiat, Murali Karthick Baskar","submitted_at":"2018-08-06T14:00:40Z","abstract_excerpt":"Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not possible. In this paper we propose a residual memory neural network (RMN) architecture to model short-time dependencies using deep feed-forward layers having residual and time delayed connections. The residual connection paves way to construct deeper networks by enabling unhindered f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01916","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":"1808.01916","created_at":"2026-05-18T00:08:49.223188+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01916v1","created_at":"2026-05-18T00:08:49.223188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01916","created_at":"2026-05-18T00:08:49.223188+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUWYWMRBE5NV","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUWYWMRBE5NVOBFZ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUWYWMRB","created_at":"2026-05-18T12:33:04.347982+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/YUWYWMRBE5NVOBFZVUORRCPVK4","json":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4.json","graph_json":"https://pith.science/api/pith-number/YUWYWMRBE5NVOBFZVUORRCPVK4/graph.json","events_json":"https://pith.science/api/pith-number/YUWYWMRBE5NVOBFZVUORRCPVK4/events.json","paper":"https://pith.science/paper/YUWYWMRB"},"agent_actions":{"view_html":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4","download_json":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4.json","view_paper":"https://pith.science/paper/YUWYWMRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01916&json=true","fetch_graph":"https://pith.science/api/pith-number/YUWYWMRBE5NVOBFZVUORRCPVK4/graph.json","fetch_events":"https://pith.science/api/pith-number/YUWYWMRBE5NVOBFZVUORRCPVK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4/action/storage_attestation","attest_author":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4/action/author_attestation","sign_citation":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4/action/citation_signature","submit_replication":"https://pith.science/pith/YUWYWMRBE5NVOBFZVUORRCPVK4/action/replication_record"}},"created_at":"2026-05-18T00:08:49.223188+00:00","updated_at":"2026-05-18T00:08:49.223188+00:00"}