{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UJSQSPJOOGKMAPAVR4MLFPYFJN","short_pith_number":"pith:UJSQSPJO","schema_version":"1.0","canonical_sha256":"a265093d2e7194c03c158f18b2bf054b42d2f039f719f6f83664ffaec4481d2c","source":{"kind":"arxiv","id":"2210.11807","version":1},"attestation_state":"computed","paper":{"title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Herold, Hermann Ney, Yingbo Gao, Zijian Yang","submitted_at":"2022-10-21T08:33:55Z","abstract_excerpt":"Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction and development of attention mechanism, encoder-decoder is still the de facto neural network architecture for state-of-the-art models. While the motivation for decoding information from some hidden space is straightforward, the strict separation of the encoding and decoding steps into an encoder and a decoder in the model architecture is not necessarily a must. Compared to the t"},"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":"2210.11807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T08:33:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"21405733673c5b89448a520f81581c01542cc0d2eec132844df403bbc277b25b","abstract_canon_sha256":"baf022b8a109a00ec67b3ffe4a88556be01a6415f70d93409c1949a479bdc8b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:57.901977Z","signature_b64":"qMzB3fFEtLYfMPfGPE8QxvBod+5lphWpFlQc6ScIvUrcmqo7vhf6fSqUaxJAVYpnw72KPK4Do9s79BPBswUnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a265093d2e7194c03c158f18b2bf054b42d2f039f719f6f83664ffaec4481d2c","last_reissued_at":"2026-07-05T05:08:57.901553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:57.901553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Herold, Hermann Ney, Yingbo Gao, Zijian Yang","submitted_at":"2022-10-21T08:33:55Z","abstract_excerpt":"Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction and development of attention mechanism, encoder-decoder is still the de facto neural network architecture for state-of-the-art models. While the motivation for decoding information from some hidden space is straightforward, the strict separation of the encoding and decoding steps into an encoder and a decoder in the model architecture is not necessarily a must. Compared to the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11807","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/2210.11807/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":"2210.11807","created_at":"2026-07-05T05:08:57.901613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11807v1","created_at":"2026-07-05T05:08:57.901613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11807","created_at":"2026-07-05T05:08:57.901613+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJSQSPJOOGKM","created_at":"2026-07-05T05:08:57.901613+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJSQSPJOOGKMAPAV","created_at":"2026-07-05T05:08:57.901613+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJSQSPJO","created_at":"2026-07-05T05:08:57.901613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16078","citing_title":"Small Language Models in the Real World: Insights from Industrial Text Classification","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN","json":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN.json","graph_json":"https://pith.science/api/pith-number/UJSQSPJOOGKMAPAVR4MLFPYFJN/graph.json","events_json":"https://pith.science/api/pith-number/UJSQSPJOOGKMAPAVR4MLFPYFJN/events.json","paper":"https://pith.science/paper/UJSQSPJO"},"agent_actions":{"view_html":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN","download_json":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN.json","view_paper":"https://pith.science/paper/UJSQSPJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11807&json=true","fetch_graph":"https://pith.science/api/pith-number/UJSQSPJOOGKMAPAVR4MLFPYFJN/graph.json","fetch_events":"https://pith.science/api/pith-number/UJSQSPJOOGKMAPAVR4MLFPYFJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN/action/storage_attestation","attest_author":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN/action/author_attestation","sign_citation":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN/action/citation_signature","submit_replication":"https://pith.science/pith/UJSQSPJOOGKMAPAVR4MLFPYFJN/action/replication_record"}},"created_at":"2026-07-05T05:08:57.901613+00:00","updated_at":"2026-07-05T05:08:57.901613+00:00"}