{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:KDH62YZRUM3OQ375JZRCF5QD2Z","short_pith_number":"pith:KDH62YZR","schema_version":"1.0","canonical_sha256":"50cfed6331a336e86ffd4e6222f603d65f2e3c128928553927f4ae80d35305c8","source":{"kind":"arxiv","id":"1311.6091","version":3},"attestation_state":"computed","paper":{"title":"A Primal-Dual Method for Training Recurrent Neural Networks Constrained by the Echo-State Property","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Jianshu Chen, Li Deng","submitted_at":"2013-11-24T08:04:41Z","abstract_excerpt":"We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via auto-regression (AR) and moving-average (MA), respectively. The focus of this paper is a primal-dual training method that formulates the learning of the RNN as a formal optimization problem with an inequality constraint that provides a sufficient condition for the stability of the network dynamics. Experimental results demonstrate the effectiveness of this new method, whi"},"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":"1311.6091","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-24T08:04:41Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c16b1edeb5f00af14dab109028857815ee638d21b3d2bc9b7537af040174c1ea","abstract_canon_sha256":"b97018206061c4e2e9a244ff58e96224383bb1baca45d90bc730d3d427f6d97b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:59.607709Z","signature_b64":"ANF4FXfeGosTGB2q3SA7pfYtKqF3d42NwIdV0XZABaMKELWm2GFeXwTxtuiwQ3Ea8ldxZy6Bu7i6d85pZyMRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50cfed6331a336e86ffd4e6222f603d65f2e3c128928553927f4ae80d35305c8","last_reissued_at":"2026-05-18T02:56:59.607226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:59.607226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Primal-Dual Method for Training Recurrent Neural Networks Constrained by the Echo-State Property","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Jianshu Chen, Li Deng","submitted_at":"2013-11-24T08:04:41Z","abstract_excerpt":"We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via auto-regression (AR) and moving-average (MA), respectively. The focus of this paper is a primal-dual training method that formulates the learning of the RNN as a formal optimization problem with an inequality constraint that provides a sufficient condition for the stability of the network dynamics. Experimental results demonstrate the effectiveness of this new method, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.6091","kind":"arxiv","version":3},"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":"1311.6091","created_at":"2026-05-18T02:56:59.607296+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.6091v3","created_at":"2026-05-18T02:56:59.607296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.6091","created_at":"2026-05-18T02:56:59.607296+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDH62YZRUM3O","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDH62YZRUM3OQ375","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDH62YZR","created_at":"2026-05-18T12:27:49.015174+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/KDH62YZRUM3OQ375JZRCF5QD2Z","json":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z.json","graph_json":"https://pith.science/api/pith-number/KDH62YZRUM3OQ375JZRCF5QD2Z/graph.json","events_json":"https://pith.science/api/pith-number/KDH62YZRUM3OQ375JZRCF5QD2Z/events.json","paper":"https://pith.science/paper/KDH62YZR"},"agent_actions":{"view_html":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z","download_json":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z.json","view_paper":"https://pith.science/paper/KDH62YZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.6091&json=true","fetch_graph":"https://pith.science/api/pith-number/KDH62YZRUM3OQ375JZRCF5QD2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KDH62YZRUM3OQ375JZRCF5QD2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z/action/storage_attestation","attest_author":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z/action/author_attestation","sign_citation":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z/action/citation_signature","submit_replication":"https://pith.science/pith/KDH62YZRUM3OQ375JZRCF5QD2Z/action/replication_record"}},"created_at":"2026-05-18T02:56:59.607296+00:00","updated_at":"2026-05-18T02:56:59.607296+00:00"}