{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3VBH3JXFULFXH4YWCFTGQ3JBJX","short_pith_number":"pith:3VBH3JXF","schema_version":"1.0","canonical_sha256":"dd427da6e5a2cb73f3161166686d214df277a2f4ffeb8101362f32287fc3a530","source":{"kind":"arxiv","id":"2306.06381","version":1},"attestation_state":"computed","paper":{"title":"INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Jingjing Xu, Lingpeng Kong, Shujian Huang, Wenhao Zhu","submitted_at":"2023-06-10T08:39:16Z","abstract_excerpt":"Neural machine translation has achieved promising results on many translation tasks. However, previous studies have shown that neural models induce a non-smooth representation space, which harms its generalization results. Recently, kNN-MT has provided an effective paradigm to smooth the prediction based on neighbor representations during inference. Despite promising results, kNN-MT usually requires large inference overhead. We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parame"},"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":"2306.06381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T08:39:16Z","cross_cats_sorted":[],"title_canon_sha256":"973d4ab39092cd4550c5cb2525069436867b01215ac6d0b7d8788bd3bbf4b71d","abstract_canon_sha256":"9bb1fb260078988d46c7f8e55aa7482f808e9c0a315b8a9b7b026436daf7709e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:24.302655Z","signature_b64":"M41jJknZrQIkOWqo44w4we8A/Uwz7iEReUUMAmOE3kFr0O3bXTK5E3NsBWNbihDfL1graMA2qw+wBS/ppjtpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd427da6e5a2cb73f3161166686d214df277a2f4ffeb8101362f32287fc3a530","last_reissued_at":"2026-07-05T06:19:24.302192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:24.302192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Jingjing Xu, Lingpeng Kong, Shujian Huang, Wenhao Zhu","submitted_at":"2023-06-10T08:39:16Z","abstract_excerpt":"Neural machine translation has achieved promising results on many translation tasks. However, previous studies have shown that neural models induce a non-smooth representation space, which harms its generalization results. Recently, kNN-MT has provided an effective paradigm to smooth the prediction based on neighbor representations during inference. Despite promising results, kNN-MT usually requires large inference overhead. We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06381","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/2306.06381/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":"2306.06381","created_at":"2026-07-05T06:19:24.302248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06381v1","created_at":"2026-07-05T06:19:24.302248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06381","created_at":"2026-07-05T06:19:24.302248+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VBH3JXFULFX","created_at":"2026-07-05T06:19:24.302248+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VBH3JXFULFXH4YW","created_at":"2026-07-05T06:19:24.302248+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VBH3JXF","created_at":"2026-07-05T06:19:24.302248+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/3VBH3JXFULFXH4YWCFTGQ3JBJX","json":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX.json","graph_json":"https://pith.science/api/pith-number/3VBH3JXFULFXH4YWCFTGQ3JBJX/graph.json","events_json":"https://pith.science/api/pith-number/3VBH3JXFULFXH4YWCFTGQ3JBJX/events.json","paper":"https://pith.science/paper/3VBH3JXF"},"agent_actions":{"view_html":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX","download_json":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX.json","view_paper":"https://pith.science/paper/3VBH3JXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06381&json=true","fetch_graph":"https://pith.science/api/pith-number/3VBH3JXFULFXH4YWCFTGQ3JBJX/graph.json","fetch_events":"https://pith.science/api/pith-number/3VBH3JXFULFXH4YWCFTGQ3JBJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX/action/storage_attestation","attest_author":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX/action/author_attestation","sign_citation":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX/action/citation_signature","submit_replication":"https://pith.science/pith/3VBH3JXFULFXH4YWCFTGQ3JBJX/action/replication_record"}},"created_at":"2026-07-05T06:19:24.302248+00:00","updated_at":"2026-07-05T06:19:24.302248+00:00"}