{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LSGFD6VSCXUPLW5ZRSBQPZZJ3M","short_pith_number":"pith:LSGFD6VS","schema_version":"1.0","canonical_sha256":"5c8c51fab215e8f5dbb98c8307e729db02d85de413bb608062b97d6b2d73ca04","source":{"kind":"arxiv","id":"1805.12096","version":1},"attestation_state":"computed","paper":{"title":"Marian: Cost-effective High-Quality Neural Machine Translation in C++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Aue, Hieu Hoang, Kenneth Heafield, Marcin Junczys-Dowmunt, Roman Grundkiewicz","submitted_at":"2018-05-30T17:23:24Z","abstract_excerpt":"This paper describes the submissions of the \"Marian\" team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task."},"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":"1805.12096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-30T17:23:24Z","cross_cats_sorted":[],"title_canon_sha256":"d9154d38c4e3851daf133e0937d8aacbf2c7f9881a017c351c69f1d746933985","abstract_canon_sha256":"e022d439246f7e7bf1919901797856761312b1eac5688192d989b9a704f1ed8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:35.225027Z","signature_b64":"X6L/k//kKpgxboH790Vfqb8riQnn8OZIYSyxsguYrPEnHm9lmalem6DMYw0C5E9pSmpfEGNGZNSHBtk6jG38Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c8c51fab215e8f5dbb98c8307e729db02d85de413bb608062b97d6b2d73ca04","last_reissued_at":"2026-05-18T00:14:35.224205Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:35.224205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Marian: Cost-effective High-Quality Neural Machine Translation in C++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Aue, Hieu Hoang, Kenneth Heafield, Marcin Junczys-Dowmunt, Roman Grundkiewicz","submitted_at":"2018-05-30T17:23:24Z","abstract_excerpt":"This paper describes the submissions of the \"Marian\" team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12096","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":"1805.12096","created_at":"2026-05-18T00:14:35.224354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.12096v1","created_at":"2026-05-18T00:14:35.224354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12096","created_at":"2026-05-18T00:14:35.224354+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSGFD6VSCXUP","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSGFD6VSCXUPLW5Z","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSGFD6VS","created_at":"2026-05-18T12:32:37.024351+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/LSGFD6VSCXUPLW5ZRSBQPZZJ3M","json":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M.json","graph_json":"https://pith.science/api/pith-number/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/graph.json","events_json":"https://pith.science/api/pith-number/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/events.json","paper":"https://pith.science/paper/LSGFD6VS"},"agent_actions":{"view_html":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M","download_json":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M.json","view_paper":"https://pith.science/paper/LSGFD6VS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.12096&json=true","fetch_graph":"https://pith.science/api/pith-number/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/graph.json","fetch_events":"https://pith.science/api/pith-number/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/action/storage_attestation","attest_author":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/action/author_attestation","sign_citation":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/action/citation_signature","submit_replication":"https://pith.science/pith/LSGFD6VSCXUPLW5ZRSBQPZZJ3M/action/replication_record"}},"created_at":"2026-05-18T00:14:35.224354+00:00","updated_at":"2026-05-18T00:14:35.224354+00:00"}