{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X36CDEQUXZEPE6PHJTEJVDVSXM","short_pith_number":"pith:X36CDEQU","canonical_record":{"source":{"id":"1909.00157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T07:35:36Z","cross_cats_sorted":[],"title_canon_sha256":"202c98de9a9a3f99c000c22cb6bcb27c2c085233f76bc006439b2b853b1a3427","abstract_canon_sha256":"0324bf5c670b695f064797afcf9fbcd755ef873fc39de30823db6546aba00266"},"schema_version":"1.0"},"canonical_sha256":"befc219214be48f279e74cc89a8eb2bb1ed5231b95c693637268f1ecf09f336e","source":{"kind":"arxiv","id":"1909.00157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00157","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00157v1","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00157","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_12","alias_value":"X36CDEQUXZEP","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_16","alias_value":"X36CDEQUXZEPE6PH","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_8","alias_value":"X36CDEQU","created_at":"2026-07-05T00:01:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X36CDEQUXZEPE6PHJTEJVDVSXM","target":"record","payload":{"canonical_record":{"source":{"id":"1909.00157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T07:35:36Z","cross_cats_sorted":[],"title_canon_sha256":"202c98de9a9a3f99c000c22cb6bcb27c2c085233f76bc006439b2b853b1a3427","abstract_canon_sha256":"0324bf5c670b695f064797afcf9fbcd755ef873fc39de30823db6546aba00266"},"schema_version":"1.0"},"canonical_sha256":"befc219214be48f279e74cc89a8eb2bb1ed5231b95c693637268f1ecf09f336e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:06.221876Z","signature_b64":"A/6Nu+iMbh7sLm53qR56CHxe0Nkz0wrJZlNo/Gqyh5FNajP1CXGSgeAVRbWeylIsriUyPITvhvG2BvqkId1JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"befc219214be48f279e74cc89a8eb2bb1ed5231b95c693637268f1ecf09f336e","last_reissued_at":"2026-07-05T00:01:06.221535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:06.221535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.00157","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":"2026-07-05T00:01:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldxJtt2qr55TSJGDBkMPF1DuRiummvfFGRhrubj9qa0oQoBrmBP0oDQZ3ruVrrUiz671pasbx1gMFDeSMdAECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:48:59.238598Z"},"content_sha256":"f5e6f1fa17a6da1aea8f99ae81eabf7cc1d67bda0be7fa8448d4fe6ebdbbe683","schema_version":"1.0","event_id":"sha256:f5e6f1fa17a6da1aea8f99ae81eabf7cc1d67bda0be7fa8448d4fe6ebdbbe683"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X36CDEQUXZEPE6PHJTEJVDVSXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Back-Translation with Uncertainty-based Confidence Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Wang, Huanbo Luan, Maosong Sun, Shuo Wang, Yang Liu","submitted_at":"2019-08-31T07:35:36Z","abstract_excerpt":"While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00157","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/1909.00157/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":"2026-07-05T00:01:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z223VBLq3latiAyHsDdbGiOY6T0NrBJNDacgoktEhPP3XdokDrQPBbhEzVf5uy1Z1+euzfMNQSsKzLb56oYjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:48:59.239089Z"},"content_sha256":"11b668f9535e1c4b44600eb1e43148fd9fb54c534e3fc95c2fa1a4dbcc32bd6e","schema_version":"1.0","event_id":"sha256:11b668f9535e1c4b44600eb1e43148fd9fb54c534e3fc95c2fa1a4dbcc32bd6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/bundle.json","state_url":"https://pith.science/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/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":"2026-08-16T21:48:59Z","links":{"resolver":"https://pith.science/pith/X36CDEQUXZEPE6PHJTEJVDVSXM","bundle":"https://pith.science/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/bundle.json","state":"https://pith.science/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X36CDEQUXZEPE6PHJTEJVDVSXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X36CDEQUXZEPE6PHJTEJVDVSXM","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":"0324bf5c670b695f064797afcf9fbcd755ef873fc39de30823db6546aba00266","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T07:35:36Z","title_canon_sha256":"202c98de9a9a3f99c000c22cb6bcb27c2c085233f76bc006439b2b853b1a3427"},"schema_version":"1.0","source":{"id":"1909.00157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00157","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00157v1","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00157","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_12","alias_value":"X36CDEQUXZEP","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_16","alias_value":"X36CDEQUXZEPE6PH","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_8","alias_value":"X36CDEQU","created_at":"2026-07-05T00:01:06Z"}],"graph_snapshots":[{"event_id":"sha256:11b668f9535e1c4b44600eb1e43148fd9fb54c534e3fc95c2fa1a4dbcc32bd6e","target":"graph","created_at":"2026-07-05T00:01:06Z","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/1909.00157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translati","authors_text":"Chao Wang, Huanbo Luan, Maosong Sun, Shuo Wang, Yang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T07:35:36Z","title":"Improving Back-Translation with Uncertainty-based Confidence Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00157","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:f5e6f1fa17a6da1aea8f99ae81eabf7cc1d67bda0be7fa8448d4fe6ebdbbe683","target":"record","created_at":"2026-07-05T00:01:06Z","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":"0324bf5c670b695f064797afcf9fbcd755ef873fc39de30823db6546aba00266","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T07:35:36Z","title_canon_sha256":"202c98de9a9a3f99c000c22cb6bcb27c2c085233f76bc006439b2b853b1a3427"},"schema_version":"1.0","source":{"id":"1909.00157","kind":"arxiv","version":1}},"canonical_sha256":"befc219214be48f279e74cc89a8eb2bb1ed5231b95c693637268f1ecf09f336e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"befc219214be48f279e74cc89a8eb2bb1ed5231b95c693637268f1ecf09f336e","first_computed_at":"2026-07-05T00:01:06.221535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:01:06.221535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A/6Nu+iMbh7sLm53qR56CHxe0Nkz0wrJZlNo/Gqyh5FNajP1CXGSgeAVRbWeylIsriUyPITvhvG2BvqkId1JCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:01:06.221876Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5e6f1fa17a6da1aea8f99ae81eabf7cc1d67bda0be7fa8448d4fe6ebdbbe683","sha256:11b668f9535e1c4b44600eb1e43148fd9fb54c534e3fc95c2fa1a4dbcc32bd6e"],"state_sha256":"277e43c413732d5690c450aab72644423a1b7b1e528f9ca58cd3d0e6048cfce6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/mh/qoq+CXc0XLDnc2KaTMoO9qPGkuKK4ygg7lxo1NcqRvU/zNjmJ++0L77DJmTf4jVO1rtaVGNTzobwbE0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:48:59.249245Z","bundle_sha256":"042621f6c3d2c5a16e3e96cd083e80260916a8195b902b6ec79b2f68c4082467"}}