{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DFB4JNLZPEA2VRNPUNSJJIKAAM","short_pith_number":"pith:DFB4JNLZ","schema_version":"1.0","canonical_sha256":"1943c4b5797901aac5afa36494a140032b3ae029cd083efe7c75a2eeaa27e045","source":{"kind":"arxiv","id":"2212.00228","version":2},"attestation_state":"computed","paper":{"title":"Gated Recurrent Neural Networks with Weighted Time-Delay Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim","submitted_at":"2022-12-01T02:26:34Z","abstract_excerpt":"In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism. Our proposed model, named $\\tau$-GRU, is a discretized version of a continuous-time formulation of a recurrent unit, where the dynamics are governed by delay differential equations (DDEs). We prove the existence and uniqueness of solutions for the continuous-time model and show that the proposed feedback mechanism can significantly improve the modeling of long-term dependencies. Our empirical results indicate"},"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":"2212.00228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T02:26:34Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b7a4c7e0af71c3e2a3b99efc785555117918d5f3f4db70eea4146f048256acac","abstract_canon_sha256":"9170e51aa54fbb63a95fd0c94b40150081e4de48a688bb062b4d9cb668251406"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:30.947064Z","signature_b64":"FjmACWWAjESI/bN/ii8ho5qtAPPtnlJYDuKXs2f7/DDTrxe8oLkpiOL6RI5zr3h4qFmGLoaStOb3Qj++HgOGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1943c4b5797901aac5afa36494a140032b3ae029cd083efe7c75a2eeaa27e045","last_reissued_at":"2026-07-05T11:05:30.946576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:30.946576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gated Recurrent Neural Networks with Weighted Time-Delay Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim","submitted_at":"2022-12-01T02:26:34Z","abstract_excerpt":"In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism. Our proposed model, named $\\tau$-GRU, is a discretized version of a continuous-time formulation of a recurrent unit, where the dynamics are governed by delay differential equations (DDEs). We prove the existence and uniqueness of solutions for the continuous-time model and show that the proposed feedback mechanism can significantly improve the modeling of long-term dependencies. Our empirical results indicate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00228","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.00228/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2212.00228","created_at":"2026-07-05T11:05:30.946633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00228v2","created_at":"2026-07-05T11:05:30.946633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00228","created_at":"2026-07-05T11:05:30.946633+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFB4JNLZPEA2","created_at":"2026-07-05T11:05:30.946633+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFB4JNLZPEA2VRNP","created_at":"2026-07-05T11:05:30.946633+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFB4JNLZ","created_at":"2026-07-05T11:05:30.946633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14980","citing_title":"A Deep State Space Model for Rainfall-Runoff Simulations","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM","json":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM.json","graph_json":"https://pith.science/api/pith-number/DFB4JNLZPEA2VRNPUNSJJIKAAM/graph.json","events_json":"https://pith.science/api/pith-number/DFB4JNLZPEA2VRNPUNSJJIKAAM/events.json","paper":"https://pith.science/paper/DFB4JNLZ"},"agent_actions":{"view_html":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM","download_json":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM.json","view_paper":"https://pith.science/paper/DFB4JNLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00228&json=true","fetch_graph":"https://pith.science/api/pith-number/DFB4JNLZPEA2VRNPUNSJJIKAAM/graph.json","fetch_events":"https://pith.science/api/pith-number/DFB4JNLZPEA2VRNPUNSJJIKAAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM/action/storage_attestation","attest_author":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM/action/author_attestation","sign_citation":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM/action/citation_signature","submit_replication":"https://pith.science/pith/DFB4JNLZPEA2VRNPUNSJJIKAAM/action/replication_record"}},"created_at":"2026-07-05T11:05:30.946633+00:00","updated_at":"2026-07-05T11:05:30.946633+00:00"}