{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FIMDK5PATUIJ4XYNBZY74LZJUO","short_pith_number":"pith:FIMDK5PA","schema_version":"1.0","canonical_sha256":"2a183575e09d109e5f0d0e71fe2f29a3b3010d0fda4d67b51a3dc83f06022198","source":{"kind":"arxiv","id":"1711.02132","version":1},"attestation_state":"computed","paper":{"title":"Weighted Transformer Network for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Karim Ahmed, Nitish Shirish Keskar, Richard Socher","submitted_at":"2017-11-06T19:35:00Z","abstract_excerpt":"State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution completely. Instead, it uses only self-attention and feed-forward layers. While the proposed architecture achieves state-of-the-art results on several machine translation tasks, it requires a large number of parameters and training iterations to converge. We propose Weighted Transformer, a Transformer with modified attention layers, that not only outperforms th"},"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":"1711.02132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-06T19:35:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c3c8e5ba7cfc0dbb0c378100604c8f7e6e9db8167c6dcedb50e71b48dcb708a2","abstract_canon_sha256":"afa8edd024eb158ad95fc8425e6bf244ba4a527642ab78a0a985e114e6573c4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:10.909288Z","signature_b64":"MH6fktfyeCpCi+OMcky3SZuseJbmr/HY576LHVxP1TCVgAOyLzF8UKQw9HNYhcf2PNdeB+wxkVsCcSIXeCtMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a183575e09d109e5f0d0e71fe2f29a3b3010d0fda4d67b51a3dc83f06022198","last_reissued_at":"2026-05-18T00:31:10.908625Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:10.908625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Transformer Network for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Karim Ahmed, Nitish Shirish Keskar, Richard Socher","submitted_at":"2017-11-06T19:35:00Z","abstract_excerpt":"State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution completely. Instead, it uses only self-attention and feed-forward layers. While the proposed architecture achieves state-of-the-art results on several machine translation tasks, it requires a large number of parameters and training iterations to converge. We propose Weighted Transformer, a Transformer with modified attention layers, that not only outperforms th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02132","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":"1711.02132","created_at":"2026-05-18T00:31:10.908737+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02132v1","created_at":"2026-05-18T00:31:10.908737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02132","created_at":"2026-05-18T00:31:10.908737+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIMDK5PATUIJ","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIMDK5PATUIJ4XYN","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIMDK5PA","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1807.03819","citing_title":"Universal Transformers","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO","json":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO.json","graph_json":"https://pith.science/api/pith-number/FIMDK5PATUIJ4XYNBZY74LZJUO/graph.json","events_json":"https://pith.science/api/pith-number/FIMDK5PATUIJ4XYNBZY74LZJUO/events.json","paper":"https://pith.science/paper/FIMDK5PA"},"agent_actions":{"view_html":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO","download_json":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO.json","view_paper":"https://pith.science/paper/FIMDK5PA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02132&json=true","fetch_graph":"https://pith.science/api/pith-number/FIMDK5PATUIJ4XYNBZY74LZJUO/graph.json","fetch_events":"https://pith.science/api/pith-number/FIMDK5PATUIJ4XYNBZY74LZJUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO/action/storage_attestation","attest_author":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO/action/author_attestation","sign_citation":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO/action/citation_signature","submit_replication":"https://pith.science/pith/FIMDK5PATUIJ4XYNBZY74LZJUO/action/replication_record"}},"created_at":"2026-05-18T00:31:10.908737+00:00","updated_at":"2026-05-18T00:31:10.908737+00:00"}