{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VTMTFKLKIOVY3FGIHEWXBR62TJ","short_pith_number":"pith:VTMTFKLK","schema_version":"1.0","canonical_sha256":"acd932a96a43ab8d94c8392d70c7da9a74181c3784fb647cfd16478f1e96af26","source":{"kind":"arxiv","id":"1808.08946","version":3},"attestation_state":"computed","paper":{"title":"Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annette Rios, Gongbo Tang, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2018-08-27T17:51:27Z","abstract_excerpt":"Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been speculated that this improves their ability to model long-range dependencies. However, this theoretical argument has not been tested empirically, nor have alternative explanations for their strong performance been explored in-depth. We hypothesize that the strong performance of CNNs and self-attentional networks could also be due to their ability to extract "},"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":"1808.08946","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T17:51:27Z","cross_cats_sorted":[],"title_canon_sha256":"702d7b4235e2d8d443642611b23fab14de5535737f19295b65ed12570e049bc1","abstract_canon_sha256":"d8a5ddb7d51cdb736d31f502a856bc04c62b5e8576865538f18dd3bb9385deb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:06.895995Z","signature_b64":"omui5UH4rS9JHOMxp4qFugnWE3pMSKgYBIT+AbOrDRTW0OCMXjhClwfDsNf3YxSPhoFJtZb1PKFco5678o02Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acd932a96a43ab8d94c8392d70c7da9a74181c3784fb647cfd16478f1e96af26","last_reissued_at":"2026-05-18T00:01:06.895396Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:06.895396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annette Rios, Gongbo Tang, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2018-08-27T17:51:27Z","abstract_excerpt":"Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been speculated that this improves their ability to model long-range dependencies. However, this theoretical argument has not been tested empirically, nor have alternative explanations for their strong performance been explored in-depth. We hypothesize that the strong performance of CNNs and self-attentional networks could also be due to their ability to extract "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08946","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":"1808.08946","created_at":"2026-05-18T00:01:06.895477+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08946v3","created_at":"2026-05-18T00:01:06.895477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08946","created_at":"2026-05-18T00:01:06.895477+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTMTFKLKIOVY","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTMTFKLKIOVY3FGI","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTMTFKLK","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12284","citing_title":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ","json":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ.json","graph_json":"https://pith.science/api/pith-number/VTMTFKLKIOVY3FGIHEWXBR62TJ/graph.json","events_json":"https://pith.science/api/pith-number/VTMTFKLKIOVY3FGIHEWXBR62TJ/events.json","paper":"https://pith.science/paper/VTMTFKLK"},"agent_actions":{"view_html":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ","download_json":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ.json","view_paper":"https://pith.science/paper/VTMTFKLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08946&json=true","fetch_graph":"https://pith.science/api/pith-number/VTMTFKLKIOVY3FGIHEWXBR62TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VTMTFKLKIOVY3FGIHEWXBR62TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ/action/storage_attestation","attest_author":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ/action/author_attestation","sign_citation":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ/action/citation_signature","submit_replication":"https://pith.science/pith/VTMTFKLKIOVY3FGIHEWXBR62TJ/action/replication_record"}},"created_at":"2026-05-18T00:01:06.895477+00:00","updated_at":"2026-05-18T00:01:06.895477+00:00"}