{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UDJRK37ICQV2RVI4FBFYFTOHH3","short_pith_number":"pith:UDJRK37I","schema_version":"1.0","canonical_sha256":"a0d3156fe8142ba8d51c284b82cdc73ef67793401f996d526999f4072d2ce4ac","source":{"kind":"arxiv","id":"1803.06585","version":1},"attestation_state":"computed","paper":{"title":"Learning Long Term Dependencies via Fourier Recurrent Units","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Inderjit S. Dhillon, Jiong Zhang, Yibo Lin, Zhao Song","submitted_at":"2018-03-17T23:06:31Z","abstract_excerpt":"It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, the Fourier Recurrent Unit (FRU), that stabilizes the gradients that arise in its training while giving us stronger expressive power. Specifically, FRU summarizes the hidden states $h^{(t)}$ along the temporal dimension with Fourier basis functions. This allows gradients to easily "},"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":"1803.06585","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-17T23:06:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b6e539556b6f0d993777b93373e84757e721186110a84e18fc809d472cb8467e","abstract_canon_sha256":"e6bda924fcc6f15ccbb9c3fae56358a438336308c3978a374247a60ac5f67ef0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:45.540343Z","signature_b64":"TR1eyc/0e1qkI/HMzvKvS72sOAwVBNUcopza/WA6M2T4Zv3/9u6Yh/KAUAmIV7xM6p7rwmxFTHig6NAVoFT/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d3156fe8142ba8d51c284b82cdc73ef67793401f996d526999f4072d2ce4ac","last_reissued_at":"2026-05-18T00:20:45.539818Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:45.539818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Long Term Dependencies via Fourier Recurrent Units","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Inderjit S. Dhillon, Jiong Zhang, Yibo Lin, Zhao Song","submitted_at":"2018-03-17T23:06:31Z","abstract_excerpt":"It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, the Fourier Recurrent Unit (FRU), that stabilizes the gradients that arise in its training while giving us stronger expressive power. Specifically, FRU summarizes the hidden states $h^{(t)}$ along the temporal dimension with Fourier basis functions. This allows gradients to easily "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06585","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":"1803.06585","created_at":"2026-05-18T00:20:45.539909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06585v1","created_at":"2026-05-18T00:20:45.539909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06585","created_at":"2026-05-18T00:20:45.539909+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDJRK37ICQV2","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDJRK37ICQV2RVI4","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDJRK37I","created_at":"2026-05-18T12:32:56.356000+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/UDJRK37ICQV2RVI4FBFYFTOHH3","json":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3.json","graph_json":"https://pith.science/api/pith-number/UDJRK37ICQV2RVI4FBFYFTOHH3/graph.json","events_json":"https://pith.science/api/pith-number/UDJRK37ICQV2RVI4FBFYFTOHH3/events.json","paper":"https://pith.science/paper/UDJRK37I"},"agent_actions":{"view_html":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3","download_json":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3.json","view_paper":"https://pith.science/paper/UDJRK37I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06585&json=true","fetch_graph":"https://pith.science/api/pith-number/UDJRK37ICQV2RVI4FBFYFTOHH3/graph.json","fetch_events":"https://pith.science/api/pith-number/UDJRK37ICQV2RVI4FBFYFTOHH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3/action/storage_attestation","attest_author":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3/action/author_attestation","sign_citation":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3/action/citation_signature","submit_replication":"https://pith.science/pith/UDJRK37ICQV2RVI4FBFYFTOHH3/action/replication_record"}},"created_at":"2026-05-18T00:20:45.539909+00:00","updated_at":"2026-05-18T00:20:45.539909+00:00"}