{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EAFSOWWTLKXWVB5DPNRVUNPNNX","short_pith_number":"pith:EAFSOWWT","schema_version":"1.0","canonical_sha256":"200b275ad35aaf6a87a37b635a35ed6dcd17debf65bb7432549e4bdc3c523b54","source":{"kind":"arxiv","id":"1911.01933","version":1},"attestation_state":"computed","paper":{"title":"Training Neural Machine Translation (NMT) Models using Tensor Train Decomposition on TensorFlow (T3F)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Heinecke, Amelia Drew","submitted_at":"2019-11-05T16:48:30Z","abstract_excerpt":"We implement a Tensor Train layer in the TensorFlow Neural Machine Translation (NMT) model using the t3f library. We perform training runs on the IWSLT English-Vietnamese '15 and WMT German-English '16 datasets with learning rates $\\in \\{0.0004,0.0008,0.0012\\}$, maximum ranks $\\in \\{2,4,8,16\\}$ and a range of core dimensions. We compare against a target BLEU test score of 24.0, obtained by our benchmark run. For the IWSLT English-Vietnamese training, we obtain BLEU test/dev scores of 24.0/21.9 and 24.2/21.9 using core dimensions $(2, 2, 256) \\times (2, 2, 512)$ with learning rate 0.0012 and ra"},"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":"1911.01933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T16:48:30Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"a9ec152f4a63daa204757ffc6df0a5782a7c42b76b8c3a2770f04feb62fa6ef2","abstract_canon_sha256":"8f17bb2d9afa3d2c8ebbf66d7d0661bb946498ed50651622714209071d98f3a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:23.174271Z","signature_b64":"hi3ets2T3uRO2mFo74VByeMhYzdWYe6/T4k7tmGH44Uw50wGXntUUE+AnnBvgwXwNQaBwOAJHc6i6dQkBNraAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"200b275ad35aaf6a87a37b635a35ed6dcd17debf65bb7432549e4bdc3c523b54","last_reissued_at":"2026-07-05T00:17:23.173845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:23.173845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural Machine Translation (NMT) Models using Tensor Train Decomposition on TensorFlow (T3F)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Heinecke, Amelia Drew","submitted_at":"2019-11-05T16:48:30Z","abstract_excerpt":"We implement a Tensor Train layer in the TensorFlow Neural Machine Translation (NMT) model using the t3f library. We perform training runs on the IWSLT English-Vietnamese '15 and WMT German-English '16 datasets with learning rates $\\in \\{0.0004,0.0008,0.0012\\}$, maximum ranks $\\in \\{2,4,8,16\\}$ and a range of core dimensions. We compare against a target BLEU test score of 24.0, obtained by our benchmark run. For the IWSLT English-Vietnamese training, we obtain BLEU test/dev scores of 24.0/21.9 and 24.2/21.9 using core dimensions $(2, 2, 256) \\times (2, 2, 512)$ with learning rate 0.0012 and ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01933","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.01933/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":"1911.01933","created_at":"2026-07-05T00:17:23.173899+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.01933v1","created_at":"2026-07-05T00:17:23.173899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01933","created_at":"2026-07-05T00:17:23.173899+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAFSOWWTLKXW","created_at":"2026-07-05T00:17:23.173899+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAFSOWWTLKXWVB5D","created_at":"2026-07-05T00:17:23.173899+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAFSOWWT","created_at":"2026-07-05T00:17:23.173899+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/EAFSOWWTLKXWVB5DPNRVUNPNNX","json":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX.json","graph_json":"https://pith.science/api/pith-number/EAFSOWWTLKXWVB5DPNRVUNPNNX/graph.json","events_json":"https://pith.science/api/pith-number/EAFSOWWTLKXWVB5DPNRVUNPNNX/events.json","paper":"https://pith.science/paper/EAFSOWWT"},"agent_actions":{"view_html":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX","download_json":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX.json","view_paper":"https://pith.science/paper/EAFSOWWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.01933&json=true","fetch_graph":"https://pith.science/api/pith-number/EAFSOWWTLKXWVB5DPNRVUNPNNX/graph.json","fetch_events":"https://pith.science/api/pith-number/EAFSOWWTLKXWVB5DPNRVUNPNNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX/action/storage_attestation","attest_author":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX/action/author_attestation","sign_citation":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX/action/citation_signature","submit_replication":"https://pith.science/pith/EAFSOWWTLKXWVB5DPNRVUNPNNX/action/replication_record"}},"created_at":"2026-07-05T00:17:23.173899+00:00","updated_at":"2026-07-05T00:17:23.173899+00:00"}