{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IIUY3BCEWFQ2QINHMN7TW27ZDI","short_pith_number":"pith:IIUY3BCE","schema_version":"1.0","canonical_sha256":"42298d8444b161a821a7637f3b6bf91a25124bcea1991f3c11a446667510def9","source":{"kind":"arxiv","id":"2204.09269","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Junliang Guo, Juntao Li, Lijun Wu, Min Zhang, Tao Qin, Tie-Yan Liu, Yisheng Xiao","submitted_at":"2022-04-20T07:25:22Z","abstract_excerpt":"Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, autoregressive (AR) generation. In recent years, many new models and algorithms have been designed/proposed to bridge the accuracy gap between NAR generation and AR generation. In this paper, we c"},"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":"2204.09269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T07:25:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ee8576fddf13b72b0582e760b24a022c69f20310fd96e6ddd022de31586be9a","abstract_canon_sha256":"32a640325fcece8f4340333232a31b8c857b9fc7f1d3377eb0d203adb44233c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:12.963575Z","signature_b64":"iO3RxpTpTuqye2tQu0I42xh49W+pfs39gfQ6PIOrg5yf88DzKQKA/I9CsXezDxm8/gql3L55kB++BeTDMxhlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42298d8444b161a821a7637f3b6bf91a25124bcea1991f3c11a446667510def9","last_reissued_at":"2026-07-05T06:28:12.963202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:12.963202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Junliang Guo, Juntao Li, Lijun Wu, Min Zhang, Tao Qin, Tie-Yan Liu, Yisheng Xiao","submitted_at":"2022-04-20T07:25:22Z","abstract_excerpt":"Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, autoregressive (AR) generation. In recent years, many new models and algorithms have been designed/proposed to bridge the accuracy gap between NAR generation and AR generation. In this paper, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09269","kind":"arxiv","version":2},"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/2204.09269/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":"2204.09269","created_at":"2026-07-05T06:28:12.963258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09269v2","created_at":"2026-07-05T06:28:12.963258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09269","created_at":"2026-07-05T06:28:12.963258+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIUY3BCEWFQ2","created_at":"2026-07-05T06:28:12.963258+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIUY3BCEWFQ2QINH","created_at":"2026-07-05T06:28:12.963258+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIUY3BCE","created_at":"2026-07-05T06:28:12.963258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.17762","citing_title":"Massive Activations in Large Language Models","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI","json":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI.json","graph_json":"https://pith.science/api/pith-number/IIUY3BCEWFQ2QINHMN7TW27ZDI/graph.json","events_json":"https://pith.science/api/pith-number/IIUY3BCEWFQ2QINHMN7TW27ZDI/events.json","paper":"https://pith.science/paper/IIUY3BCE"},"agent_actions":{"view_html":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI","download_json":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI.json","view_paper":"https://pith.science/paper/IIUY3BCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09269&json=true","fetch_graph":"https://pith.science/api/pith-number/IIUY3BCEWFQ2QINHMN7TW27ZDI/graph.json","fetch_events":"https://pith.science/api/pith-number/IIUY3BCEWFQ2QINHMN7TW27ZDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI/action/storage_attestation","attest_author":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI/action/author_attestation","sign_citation":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI/action/citation_signature","submit_replication":"https://pith.science/pith/IIUY3BCEWFQ2QINHMN7TW27ZDI/action/replication_record"}},"created_at":"2026-07-05T06:28:12.963258+00:00","updated_at":"2026-07-05T06:28:12.963258+00:00"}