{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TNGWUNZDC4YI3RI63CGXIVLSPT","short_pith_number":"pith:TNGWUNZD","schema_version":"1.0","canonical_sha256":"9b4d6a372317308dc51ed88d7455727ce2da65ab899705e6c66b31f394994b25","source":{"kind":"arxiv","id":"2003.11660","version":2},"attestation_state":"computed","paper":{"title":"R-FORCE: Robust Learning for Random Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Eli Shlizerman, Yang Zheng","submitted_at":"2020-03-25T22:08:03Z","abstract_excerpt":"Random Recurrent Neural Networks (RRNN) are the simplest recurrent networks to model and extract features from sequential data. The simplicity however comes with a price; RRNN are known to be susceptible to diminishing/exploding gradient problem when trained with gradient-descent based optimization. To enhance robustness of RRNN, alternative training approaches have been proposed. Specifically, FORCE learning approach proposed a recursive least squares alternative to train RRNN and was shown to be applicable even for the challenging task of target-learning, where the network is tasked with gen"},"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":"2003.11660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T22:08:03Z","cross_cats_sorted":["cs.NE","q-bio.NC"],"title_canon_sha256":"bea617f6087d4279afc4bea710625a3f9800a5a5816b6ab9ae81d6cd49c7b8fe","abstract_canon_sha256":"48233edce67706ee881dc2c2ed38ca93343650d23250f3ea188ce0aa2b2ea0be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:09.280764Z","signature_b64":"wDABrLweo23pSC4XDWdA9dwrkp587UoYBo5l6gMitGs8tbGDXEaGUm35OXlEHJlavAHalKt8nAwiae1vgpUBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4d6a372317308dc51ed88d7455727ce2da65ab899705e6c66b31f394994b25","last_reissued_at":"2026-07-05T11:18:09.280270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:09.280270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R-FORCE: Robust Learning for Random Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Eli Shlizerman, Yang Zheng","submitted_at":"2020-03-25T22:08:03Z","abstract_excerpt":"Random Recurrent Neural Networks (RRNN) are the simplest recurrent networks to model and extract features from sequential data. The simplicity however comes with a price; RRNN are known to be susceptible to diminishing/exploding gradient problem when trained with gradient-descent based optimization. To enhance robustness of RRNN, alternative training approaches have been proposed. Specifically, FORCE learning approach proposed a recursive least squares alternative to train RRNN and was shown to be applicable even for the challenging task of target-learning, where the network is tasked with gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11660","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/2003.11660/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":"2003.11660","created_at":"2026-07-05T11:18:09.280337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11660v2","created_at":"2026-07-05T11:18:09.280337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11660","created_at":"2026-07-05T11:18:09.280337+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNGWUNZDC4YI","created_at":"2026-07-05T11:18:09.280337+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNGWUNZDC4YI3RI6","created_at":"2026-07-05T11:18:09.280337+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNGWUNZD","created_at":"2026-07-05T11:18:09.280337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07975","citing_title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT","json":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT.json","graph_json":"https://pith.science/api/pith-number/TNGWUNZDC4YI3RI63CGXIVLSPT/graph.json","events_json":"https://pith.science/api/pith-number/TNGWUNZDC4YI3RI63CGXIVLSPT/events.json","paper":"https://pith.science/paper/TNGWUNZD"},"agent_actions":{"view_html":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT","download_json":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT.json","view_paper":"https://pith.science/paper/TNGWUNZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11660&json=true","fetch_graph":"https://pith.science/api/pith-number/TNGWUNZDC4YI3RI63CGXIVLSPT/graph.json","fetch_events":"https://pith.science/api/pith-number/TNGWUNZDC4YI3RI63CGXIVLSPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT/action/storage_attestation","attest_author":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT/action/author_attestation","sign_citation":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT/action/citation_signature","submit_replication":"https://pith.science/pith/TNGWUNZDC4YI3RI63CGXIVLSPT/action/replication_record"}},"created_at":"2026-07-05T11:18:09.280337+00:00","updated_at":"2026-07-05T11:18:09.280337+00:00"}