{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PLSGVRNRF52B7AWYQB3IETNPEQ","short_pith_number":"pith:PLSGVRNR","schema_version":"1.0","canonical_sha256":"7ae46ac5b12f741f82d88076824daf2421ea5f6ab09b0abe06c761d450bdd2c4","source":{"kind":"arxiv","id":"1810.12546","version":1},"attestation_state":"computed","paper":{"title":"Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Deyi Xiong, Huiji Zhang, Jinsong Su, Qian Lin","submitted_at":"2018-10-30T06:55:23Z","abstract_excerpt":"In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs. With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated. Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved. Additionally, the proposed ATR is more transparent than LSTM/G"},"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":"1810.12546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T06:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"24151c56f0b32efc9bf87d4b473e140477cc703f85e4b790f8cd47333d45059b","abstract_canon_sha256":"d838581b0a8c597d81339d43756d714bfd39de6c937a3e54baed2b854e992410"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:56.765471Z","signature_b64":"hnMBl0XdgjSdn4ulXsbfa5G/VKBSkVqeb3TPqjI1u24eaM6DVq0y+WAsi2Nw/uoyLaMn/vzXn/7YJ2bRNEf5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae46ac5b12f741f82d88076824daf2421ea5f6ab09b0abe06c761d450bdd2c4","last_reissued_at":"2026-05-18T00:01:56.764876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:56.764876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Deyi Xiong, Huiji Zhang, Jinsong Su, Qian Lin","submitted_at":"2018-10-30T06:55:23Z","abstract_excerpt":"In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs. With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated. Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved. Additionally, the proposed ATR is more transparent than LSTM/G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12546","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":"1810.12546","created_at":"2026-05-18T00:01:56.764964+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12546v1","created_at":"2026-05-18T00:01:56.764964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12546","created_at":"2026-05-18T00:01:56.764964+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLSGVRNRF52B","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLSGVRNRF52B7AWY","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLSGVRNR","created_at":"2026-05-18T12:32:46.962924+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/PLSGVRNRF52B7AWYQB3IETNPEQ","json":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ.json","graph_json":"https://pith.science/api/pith-number/PLSGVRNRF52B7AWYQB3IETNPEQ/graph.json","events_json":"https://pith.science/api/pith-number/PLSGVRNRF52B7AWYQB3IETNPEQ/events.json","paper":"https://pith.science/paper/PLSGVRNR"},"agent_actions":{"view_html":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ","download_json":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ.json","view_paper":"https://pith.science/paper/PLSGVRNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12546&json=true","fetch_graph":"https://pith.science/api/pith-number/PLSGVRNRF52B7AWYQB3IETNPEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PLSGVRNRF52B7AWYQB3IETNPEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ/action/storage_attestation","attest_author":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ/action/author_attestation","sign_citation":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ/action/citation_signature","submit_replication":"https://pith.science/pith/PLSGVRNRF52B7AWYQB3IETNPEQ/action/replication_record"}},"created_at":"2026-05-18T00:01:56.764964+00:00","updated_at":"2026-05-18T00:01:56.764964+00:00"}