{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ACQJIQVD7VDJJNEZHHC7DWLKZU","short_pith_number":"pith:ACQJIQVD","canonical_record":{"source":{"id":"2106.00941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T05:01:36Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"3a2152a194b64b76398e9482eaa0a4d2df6b1ab396a2f0d3cd627e23e94db7c2","abstract_canon_sha256":"c5bdf4b6146adad6099da0b4ee883b94f5266c2d039900fa44e1a9970a668463"},"schema_version":"1.0"},"canonical_sha256":"00a09442a3fd4694b49939c5f1d96acd0d6525fe6ad1764ae01786afe5367ff2","source":{"kind":"arxiv","id":"2106.00941","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00941","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00941v1","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00941","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"ACQJIQVD7VDJ","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"ACQJIQVD7VDJJNEZ","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"ACQJIQVD","created_at":"2026-07-05T02:45:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ACQJIQVD7VDJJNEZHHC7DWLKZU","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T05:01:36Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"3a2152a194b64b76398e9482eaa0a4d2df6b1ab396a2f0d3cd627e23e94db7c2","abstract_canon_sha256":"c5bdf4b6146adad6099da0b4ee883b94f5266c2d039900fa44e1a9970a668463"},"schema_version":"1.0"},"canonical_sha256":"00a09442a3fd4694b49939c5f1d96acd0d6525fe6ad1764ae01786afe5367ff2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:41.848911Z","signature_b64":"MVWoyCrSHCBcw5yjnpXETHgD19oMqRlyGTYnMT1yE6BlZfCKad460NExM7wVc10q1eFu0noi/mb5SDFpUtnWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a09442a3fd4694b49939c5f1d96acd0d6525fe6ad1764ae01786afe5367ff2","last_reissued_at":"2026-07-05T02:45:41.848496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:41.848496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00941","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":"2026-07-05T02:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K2UG5eTsLBSodNMfTyL6+76D43I05vC4+JjwMek25ngLlvXi0dtovE/KXItemBwXrE4ep5rZjWDkMD0nz3OcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:39:06.404937Z"},"content_sha256":"d6cb6fc7793810f26bc52137ecf619140daea7d591e6f9cf22911f74acbe0e52","schema_version":"1.0","event_id":"sha256:d6cb6fc7793810f26bc52137ecf619140daea7d591e6f9cf22911f74acbe0e52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ACQJIQVD7VDJJNEZHHC7DWLKZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Irwin King, Michael R. Lyu, Shuming Shi, Wenxiang Jiao, Xing Wang, Zhaopeng Tu","submitted_at":"2021-06-02T05:01:36Z","abstract_excerpt":"Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual data, which we empirically show is sub-optimal. In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data. To this end, we compute the uncertainty of monolingual sentences using the bilingual dictionary extracted from the parallel data. Intuitively, monolingual sentences wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00941","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/2106.00941/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":"2026-07-05T02:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8GVJCvqH0Lmhhdrkk8kVbgwJSGboIZfL5E9EP1eNSuuB0JS+3Eu60C+d7oSKtO2RnnJmfENj2iJYxRd2t13CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:39:06.405514Z"},"content_sha256":"203e7970036e652c2df05b9c100ec14db9f9167c28ec77008869647f9068164c","schema_version":"1.0","event_id":"sha256:203e7970036e652c2df05b9c100ec14db9f9167c28ec77008869647f9068164c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/bundle.json","state_url":"https://pith.science/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/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":"2026-08-21T10:39:06Z","links":{"resolver":"https://pith.science/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU","bundle":"https://pith.science/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/bundle.json","state":"https://pith.science/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACQJIQVD7VDJJNEZHHC7DWLKZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ACQJIQVD7VDJJNEZHHC7DWLKZU","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":"c5bdf4b6146adad6099da0b4ee883b94f5266c2d039900fa44e1a9970a668463","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T05:01:36Z","title_canon_sha256":"3a2152a194b64b76398e9482eaa0a4d2df6b1ab396a2f0d3cd627e23e94db7c2"},"schema_version":"1.0","source":{"id":"2106.00941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00941","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00941v1","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00941","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"ACQJIQVD7VDJ","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"ACQJIQVD7VDJJNEZ","created_at":"2026-07-05T02:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"ACQJIQVD","created_at":"2026-07-05T02:45:41Z"}],"graph_snapshots":[{"event_id":"sha256:203e7970036e652c2df05b9c100ec14db9f9167c28ec77008869647f9068164c","target":"graph","created_at":"2026-07-05T02:45:41Z","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/2106.00941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual data, which we empirically show is sub-optimal. In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data. To this end, we compute the uncertainty of monolingual sentences using the bilingual dictionary extracted from the parallel data. Intuitively, monolingual sentences wi","authors_text":"Irwin King, Michael R. Lyu, Shuming Shi, Wenxiang Jiao, Xing Wang, Zhaopeng Tu","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T05:01:36Z","title":"Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00941","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:d6cb6fc7793810f26bc52137ecf619140daea7d591e6f9cf22911f74acbe0e52","target":"record","created_at":"2026-07-05T02:45:41Z","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":"c5bdf4b6146adad6099da0b4ee883b94f5266c2d039900fa44e1a9970a668463","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T05:01:36Z","title_canon_sha256":"3a2152a194b64b76398e9482eaa0a4d2df6b1ab396a2f0d3cd627e23e94db7c2"},"schema_version":"1.0","source":{"id":"2106.00941","kind":"arxiv","version":1}},"canonical_sha256":"00a09442a3fd4694b49939c5f1d96acd0d6525fe6ad1764ae01786afe5367ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00a09442a3fd4694b49939c5f1d96acd0d6525fe6ad1764ae01786afe5367ff2","first_computed_at":"2026-07-05T02:45:41.848496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:41.848496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MVWoyCrSHCBcw5yjnpXETHgD19oMqRlyGTYnMT1yE6BlZfCKad460NExM7wVc10q1eFu0noi/mb5SDFpUtnWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:41.848911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6cb6fc7793810f26bc52137ecf619140daea7d591e6f9cf22911f74acbe0e52","sha256:203e7970036e652c2df05b9c100ec14db9f9167c28ec77008869647f9068164c"],"state_sha256":"19ed774fbdcc68b12bb736ce5bc890ccb80e4d2604ea22ddf16b5b6002248c12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HrXnOGQBmgIHmvFf0Iw+ADy7GR6NZ7hZaJbWIuNj8JWYrsT5dij6KYmOO+uZBx85oNY/f5KGLN9UPpq905nCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:39:06.409405Z","bundle_sha256":"135d381546d96c67611d73de79812b4de3416035ef4263b584970e8a39e20ebb"}}