{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:B3HTIQWEX5FU476G7ZILOS4AYH","short_pith_number":"pith:B3HTIQWE","schema_version":"1.0","canonical_sha256":"0ecf3442c4bf4b4e7fc6fe50b74b80c1cb6a94a17958d7d2d7c8896c1bdab5a2","source":{"kind":"arxiv","id":"1706.02761","version":3},"attestation_state":"computed","paper":{"title":"Gated Orthogonal Recurrent Units: On Learning to Forget","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, John Peurifoy, Li Jing, Marin Solja\\v{c}i\\'c, Max Tegmark, Yichen Shen, Yoshua Bengio","submitted_at":"2017-06-08T20:40:32Z","abstract_excerpt":"We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTMs, GRUs and Unitary RNNs on several long-term dependency benchmark tasks. We empirically both show the orthogonal/unitary RNNs lack the ability to forget and also the ability of GORU to simultaneously remember long term dependencies while forgetting irrelevant information. This p"},"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":"1706.02761","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-08T20:40:32Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"1602775a9cf623d74f584640d6f6deef76f9a60128d8107c4f35dfdc086d6db8","abstract_canon_sha256":"81b8fe6b14313f35cb20d29638186e172ad2d136d3336d7eb5b558601e198892"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:01.064356Z","signature_b64":"8+l1HapApifRL/rYRuPUSwvxWvPM3JCN7UGr1xYi4+HpGUv9hnzjyY3FGJJnLETAAKp/bwhFt3fpMaevC0zhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ecf3442c4bf4b4e7fc6fe50b74b80c1cb6a94a17958d7d2d7c8896c1bdab5a2","last_reissued_at":"2026-05-18T00:32:01.063834Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:01.063834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gated Orthogonal Recurrent Units: On Learning to Forget","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, John Peurifoy, Li Jing, Marin Solja\\v{c}i\\'c, Max Tegmark, Yichen Shen, Yoshua Bengio","submitted_at":"2017-06-08T20:40:32Z","abstract_excerpt":"We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTMs, GRUs and Unitary RNNs on several long-term dependency benchmark tasks. We empirically both show the orthogonal/unitary RNNs lack the ability to forget and also the ability of GORU to simultaneously remember long term dependencies while forgetting irrelevant information. This p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02761","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":"1706.02761","created_at":"2026-05-18T00:32:01.063894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02761v3","created_at":"2026-05-18T00:32:01.063894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02761","created_at":"2026-05-18T00:32:01.063894+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3HTIQWEX5FU","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3HTIQWEX5FU476G","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3HTIQWE","created_at":"2026-05-18T12:31:08.081275+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/B3HTIQWEX5FU476G7ZILOS4AYH","json":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH.json","graph_json":"https://pith.science/api/pith-number/B3HTIQWEX5FU476G7ZILOS4AYH/graph.json","events_json":"https://pith.science/api/pith-number/B3HTIQWEX5FU476G7ZILOS4AYH/events.json","paper":"https://pith.science/paper/B3HTIQWE"},"agent_actions":{"view_html":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH","download_json":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH.json","view_paper":"https://pith.science/paper/B3HTIQWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02761&json=true","fetch_graph":"https://pith.science/api/pith-number/B3HTIQWEX5FU476G7ZILOS4AYH/graph.json","fetch_events":"https://pith.science/api/pith-number/B3HTIQWEX5FU476G7ZILOS4AYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH/action/storage_attestation","attest_author":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH/action/author_attestation","sign_citation":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH/action/citation_signature","submit_replication":"https://pith.science/pith/B3HTIQWEX5FU476G7ZILOS4AYH/action/replication_record"}},"created_at":"2026-05-18T00:32:01.063894+00:00","updated_at":"2026-05-18T00:32:01.063894+00:00"}