{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I757PMDYBXMPBL5NUPA47TMDGW","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":"33f8c986e5e31c8f7525ecfd25ca5f20d9be0f329feb1ff6a39e62a43dddc3e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-11T13:36:01Z","title_canon_sha256":"468707409e86c2569e9ffb4307edcf8327c29a4fc264afc0d0ed24ae28a1f784"},"schema_version":"1.0","source":{"id":"2106.06381","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06381","created_at":"2026-07-05T03:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06381v2","created_at":"2026-07-05T03:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06381","created_at":"2026-07-05T03:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"I757PMDYBXMP","created_at":"2026-07-05T03:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"I757PMDYBXMPBL5N","created_at":"2026-07-05T03:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"I757PMDY","created_at":"2026-07-05T03:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:d4768252cfbf824b45e9616f381a1c59fa83a6b4a6ca5380e03e5180869a810a","target":"graph","created_at":"2026-07-05T03:13:29Z","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/2106.06381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first self-labels word alignments for parallel sentences. Then we randomly mask tokens in a bitext pair. Given a masked token, the model uses a pointer network to predict the aligned token in the other language. We alternately perform the above two steps in an expectation-maximization manner. Experimental results show that our method improves cro","authors_text":"Bo Zheng, Furu Wei, Heyan Huang, Li Dong, Shaohan Huang, Xian-Ling Mao, Zewen Chi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-11T13:36:01Z","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06381","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":"sha256:943f5ed642f95d60d4602217671a50fb8c24cd25c5b1caa62e9c83a1a0241545","target":"record","created_at":"2026-07-05T03:13:29Z","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":"33f8c986e5e31c8f7525ecfd25ca5f20d9be0f329feb1ff6a39e62a43dddc3e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-11T13:36:01Z","title_canon_sha256":"468707409e86c2569e9ffb4307edcf8327c29a4fc264afc0d0ed24ae28a1f784"},"schema_version":"1.0","source":{"id":"2106.06381","kind":"arxiv","version":2}},"canonical_sha256":"47fbf7b0780dd8f0afada3c1cfcd8335abb9ba7ba4414262b6e4cb82b909ba31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47fbf7b0780dd8f0afada3c1cfcd8335abb9ba7ba4414262b6e4cb82b909ba31","first_computed_at":"2026-07-05T03:13:29.824141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:29.824141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrQOpq9+3G8W+aGdC73qrpNlNLVkuS/S2EUHaFuVkWDfLYhW1FqfgsZx2Q8TTEbUyO8SjvURrQPKmMim4/ogDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:29.824615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06381","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943f5ed642f95d60d4602217671a50fb8c24cd25c5b1caa62e9c83a1a0241545","sha256:d4768252cfbf824b45e9616f381a1c59fa83a6b4a6ca5380e03e5180869a810a"],"state_sha256":"0bab0228d1a0f2147b9d28e76c000e9c975f8e3afa19a5a7ca1411dff92e4412"}