{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IBLLN34KXU3K4HFJJMZQ6XSARR","short_pith_number":"pith:IBLLN34K","canonical_record":{"source":{"id":"2112.11640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:06:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0467866704aac1d17481d51133dd5ad2257d3f25fffc96c37b5a6567bf5ab4c","abstract_canon_sha256":"cc10b6b80fbe52bfcad8115207c4e74dd251885ee6cff42f70268aa3ba23ccb4"},"schema_version":"1.0"},"canonical_sha256":"4056b6ef8abd36ae1ca94b330f5e408c7465d889b377ded9d9bb6bd758236753","source":{"kind":"arxiv","id":"2112.11640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11640","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11640v1","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11640","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"IBLLN34KXU3K","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_16","alias_value":"IBLLN34KXU3K4HFJ","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_8","alias_value":"IBLLN34K","created_at":"2026-07-05T03:43:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IBLLN34KXU3K4HFJJMZQ6XSARR","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:06:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0467866704aac1d17481d51133dd5ad2257d3f25fffc96c37b5a6567bf5ab4c","abstract_canon_sha256":"cc10b6b80fbe52bfcad8115207c4e74dd251885ee6cff42f70268aa3ba23ccb4"},"schema_version":"1.0"},"canonical_sha256":"4056b6ef8abd36ae1ca94b330f5e408c7465d889b377ded9d9bb6bd758236753","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:09.150193Z","signature_b64":"tfUZpfyqoQW5GfCfFoMbbrrjSPTEZVdgIpK6jkBDPq6mb+JR3Ey6aZ3zZcDb3ZXL5j6P4vVBSr3K/xygmx89Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4056b6ef8abd36ae1ca94b330f5e408c7465d889b377ded9d9bb6bd758236753","last_reissued_at":"2026-07-05T03:43:09.149736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:09.149736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11640","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNT2c4SWzgF6JJLZ1eUpwjNPviWQv61CCHx8WQKWybsK7zWL95Ctm2PfwK1zrRM5on9vpAdAbUCsZBv9BiJQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:39:37.375269Z"},"content_sha256":"4b0632a0d2ec8ffca7d236164505ede5163508793ae46e2c1a4e5ba488141742","schema_version":"1.0","event_id":"sha256:4b0632a0d2ec8ffca7d236164505ede5163508793ae46e2c1a4e5ba488141742"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IBLLN34KXU3K4HFJJMZQ6XSARR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Lizhi Lei, Minghan Wang, Min Zhang, Shimin Tao, Yimeng Chen, Yuxia Wang, Zhanglin Wu, Zhengzhe Yu, Zongyao Li","submitted_at":"2021-12-22T03:06:27Z","abstract_excerpt":"Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student models on distilled data generated by AT teacher models, which is known as sequence-level Knowledge Distillation. An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11640","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/2112.11640/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sG5x0ypBoyrqhCARJiFAPFKl9+vm1+89E5/VjJUM70hs9EAQGtyCFT0DZiNGBmNHhlapAlrtPju5TfKVOdwfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:39:37.375845Z"},"content_sha256":"c3838e90eed96336ffd4f70df00fb6f9337c72e2143a6ba9624c9a3d2684cca1","schema_version":"1.0","event_id":"sha256:c3838e90eed96336ffd4f70df00fb6f9337c72e2143a6ba9624c9a3d2684cca1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/bundle.json","state_url":"https://pith.science/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T07:39:37Z","links":{"resolver":"https://pith.science/pith/IBLLN34KXU3K4HFJJMZQ6XSARR","bundle":"https://pith.science/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/bundle.json","state":"https://pith.science/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBLLN34KXU3K4HFJJMZQ6XSARR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IBLLN34KXU3K4HFJJMZQ6XSARR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cc10b6b80fbe52bfcad8115207c4e74dd251885ee6cff42f70268aa3ba23ccb4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:06:27Z","title_canon_sha256":"e0467866704aac1d17481d51133dd5ad2257d3f25fffc96c37b5a6567bf5ab4c"},"schema_version":"1.0","source":{"id":"2112.11640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11640","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11640v1","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11640","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"IBLLN34KXU3K","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_16","alias_value":"IBLLN34KXU3K4HFJ","created_at":"2026-07-05T03:43:09Z"},{"alias_kind":"pith_short_8","alias_value":"IBLLN34K","created_at":"2026-07-05T03:43:09Z"}],"graph_snapshots":[{"event_id":"sha256:c3838e90eed96336ffd4f70df00fb6f9337c72e2143a6ba9624c9a3d2684cca1","target":"graph","created_at":"2026-07-05T03:43:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.11640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student models on distilled data generated by AT teacher models, which is known as sequence-level Knowledge Distillation. An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Lizhi Lei, Minghan Wang, Min Zhang, Shimin Tao, Yimeng Chen, Yuxia Wang, Zhanglin Wu, Zhengzhe Yu, Zongyao Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:06:27Z","title":"Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11640","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b0632a0d2ec8ffca7d236164505ede5163508793ae46e2c1a4e5ba488141742","target":"record","created_at":"2026-07-05T03:43:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cc10b6b80fbe52bfcad8115207c4e74dd251885ee6cff42f70268aa3ba23ccb4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:06:27Z","title_canon_sha256":"e0467866704aac1d17481d51133dd5ad2257d3f25fffc96c37b5a6567bf5ab4c"},"schema_version":"1.0","source":{"id":"2112.11640","kind":"arxiv","version":1}},"canonical_sha256":"4056b6ef8abd36ae1ca94b330f5e408c7465d889b377ded9d9bb6bd758236753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4056b6ef8abd36ae1ca94b330f5e408c7465d889b377ded9d9bb6bd758236753","first_computed_at":"2026-07-05T03:43:09.149736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:09.149736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfUZpfyqoQW5GfCfFoMbbrrjSPTEZVdgIpK6jkBDPq6mb+JR3Ey6aZ3zZcDb3ZXL5j6P4vVBSr3K/xygmx89Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:09.150193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b0632a0d2ec8ffca7d236164505ede5163508793ae46e2c1a4e5ba488141742","sha256:c3838e90eed96336ffd4f70df00fb6f9337c72e2143a6ba9624c9a3d2684cca1"],"state_sha256":"85c26b57550713760b4c312e8cab791c4915dc26632e5af5114f2910e7ff2a08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MaqH93DVKAGLQNVTTdsAXLuuLwz/f1YNIiZHo+8ncF3iC7jHsDfAksGBHyAZCOMr2fBakFsc0991thHX7UfDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:39:37.380465Z","bundle_sha256":"bf7678ff1d37753eb851f99c80beb710894269751bb769e3437cdc62765776ac"}}