{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Z7ITT3HCAANIX6FYQWRLXLVWFT","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":"140bde004e2a4637a06d7144eaac4eee77e7edac44b930fbad7d5ec61030ef42","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:41:40Z","title_canon_sha256":"7ae60ee749be86020e9394af62ce77840982999f74ce06104ef4e6bfe05fa555"},"schema_version":"1.0","source":{"id":"2106.00903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00903","created_at":"2026-07-05T04:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00903v2","created_at":"2026-07-05T04:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00903","created_at":"2026-07-05T04:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"Z7ITT3HCAANI","created_at":"2026-07-05T04:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"Z7ITT3HCAANIX6FY","created_at":"2026-07-05T04:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"Z7ITT3HC","created_at":"2026-07-05T04:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:fc54fb1c635d149270ab6d4a6ee31b7acb1b3a661235cf9e7ef0423f777297eb","target":"graph","created_at":"2026-07-05T04:17:35Z","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/2106.00903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original data, leading to more errors on predicting low-frequency words. To alleviate the problem, we directly expose the raw data into NAT by leveraging pretraining. By analyzing directed alignments, we found that KD makes low-frequency source words aligned with targets more deterministically but fails to align sufficient low-frequency words from target to source. Accordingly,","authors_text":"Dacheng Tao, Derek F. Wong, Liang Ding, Longyue Wang, Xuebo Liu, Zhaopeng Tu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:41:40Z","title":"Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00903","kind":"arxiv","version":2},"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":"sha256:5fa83639489521af46ef552907af5d277f0b49789cd55697545c00713fdb16be","target":"record","created_at":"2026-07-05T04:17:35Z","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":"140bde004e2a4637a06d7144eaac4eee77e7edac44b930fbad7d5ec61030ef42","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:41:40Z","title_canon_sha256":"7ae60ee749be86020e9394af62ce77840982999f74ce06104ef4e6bfe05fa555"},"schema_version":"1.0","source":{"id":"2106.00903","kind":"arxiv","version":2}},"canonical_sha256":"cfd139ece2001a8bf8b885a2bbaeb62ce6088ad0c0a26266e91a36c87505bc87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfd139ece2001a8bf8b885a2bbaeb62ce6088ad0c0a26266e91a36c87505bc87","first_computed_at":"2026-07-05T04:17:35.442643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:35.442643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAebEyBhDPKwnUbRYC9dicNrmgEvRTUeevXid/2HPs/Bl6/rYPBNgqVM5g7QOLvXHLYvBRXs0PnJ8XElEW0+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:35.443113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fa83639489521af46ef552907af5d277f0b49789cd55697545c00713fdb16be","sha256:fc54fb1c635d149270ab6d4a6ee31b7acb1b3a661235cf9e7ef0423f777297eb"],"state_sha256":"ac102eb8496cd24d936f1fe74a561e81b8fb1a90f911e0b9f6a58565396a6b0e"}