{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IW2CQ6FTUSHSA5QOBEMZJAH6F3","short_pith_number":"pith:IW2CQ6FT","canonical_record":{"source":{"id":"2109.04443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T17:43:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"59acd967ba7e58b50b221088728e8dc1a78da04d36f63ec24b2d0545ee30aaac","abstract_canon_sha256":"e04af3a6572217061d4501515c2d10d7ae05a43ba587f711e30af9fc39e9f486"},"schema_version":"1.0"},"canonical_sha256":"45b42878b3a48f20760e09199480fe2ef834bd632cf6d4ac6db1e136c462aaf6","source":{"kind":"arxiv","id":"2109.04443","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04443","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04443v1","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04443","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"IW2CQ6FTUSHS","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"IW2CQ6FTUSHSA5QO","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"IW2CQ6FT","created_at":"2026-07-05T03:12:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IW2CQ6FTUSHSA5QOBEMZJAH6F3","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T17:43:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"59acd967ba7e58b50b221088728e8dc1a78da04d36f63ec24b2d0545ee30aaac","abstract_canon_sha256":"e04af3a6572217061d4501515c2d10d7ae05a43ba587f711e30af9fc39e9f486"},"schema_version":"1.0"},"canonical_sha256":"45b42878b3a48f20760e09199480fe2ef834bd632cf6d4ac6db1e136c462aaf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:58.550635Z","signature_b64":"OiYgrukAaap2wgl+qqYoKxsAitnrpaMhVaj/mkDeXEXMqU/RxpdPjmsEgfg6m5bhvt7XtnURTBM1fVsMwDuIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b42878b3a48f20760e09199480fe2ef834bd632cf6d4ac6db1e136c462aaf6","last_reissued_at":"2026-07-05T03:12:58.550195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:58.550195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04443","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":"2026-07-05T03:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J78wmxdGsxyl3DM7bme3gGo//weLDSnMjDa3ut18b0ucuwdDInXp1aVz/V4xJnU8uu4vh45T9+GZBL0fsC39Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:08:09.299057Z"},"content_sha256":"d5e8fe3e489124253f677e1164c83ff8fe932d670f2649dc32272bbc05d75414","schema_version":"1.0","event_id":"sha256:d5e8fe3e489124253f677e1164c83ff8fe932d670f2649dc32272bbc05d75414"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IW2CQ6FTUSHSA5QOBEMZJAH6F3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhirut Gupta, Aravindan Raghuveer, Melvin Johnson, Sahana Ramnath","submitted_at":"2021-09-09T17:43:20Z","abstract_excerpt":"Back-translation (BT) of target monolingual corpora is a widely used data augmentation strategy for neural machine translation (NMT), especially for low-resource language pairs. To improve effectiveness of the available BT data, we introduce HintedBT -- a family of techniques which provides hints (through tags) to the encoder and decoder. First, we propose a novel method of using both high and low quality BT data by providing hints (as source tags on the encoder) to the model about the quality of each source-target pair. We don't filter out low quality data but instead show that these hints en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04443","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/2109.04443/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":"2026-07-05T03:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gmMiDt3Mmou7BXom21JcipnfZOmxT51FBp31z+TDVDWX3at23OmzMckFxEfYMYP8dtxL1iQReZ4zv6AgmqECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:08:09.299449Z"},"content_sha256":"eb943ce6d7e8e275e88eebbf40a123ec8528976f8dbb08f043c6ff031a9e2bb3","schema_version":"1.0","event_id":"sha256:eb943ce6d7e8e275e88eebbf40a123ec8528976f8dbb08f043c6ff031a9e2bb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/bundle.json","state_url":"https://pith.science/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/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":"2026-07-07T10:08:09Z","links":{"resolver":"https://pith.science/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3","bundle":"https://pith.science/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/bundle.json","state":"https://pith.science/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IW2CQ6FTUSHSA5QOBEMZJAH6F3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IW2CQ6FTUSHSA5QOBEMZJAH6F3","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":"e04af3a6572217061d4501515c2d10d7ae05a43ba587f711e30af9fc39e9f486","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T17:43:20Z","title_canon_sha256":"59acd967ba7e58b50b221088728e8dc1a78da04d36f63ec24b2d0545ee30aaac"},"schema_version":"1.0","source":{"id":"2109.04443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04443","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04443v1","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04443","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"IW2CQ6FTUSHS","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"IW2CQ6FTUSHSA5QO","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"IW2CQ6FT","created_at":"2026-07-05T03:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:eb943ce6d7e8e275e88eebbf40a123ec8528976f8dbb08f043c6ff031a9e2bb3","target":"graph","created_at":"2026-07-05T03:12:58Z","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/2109.04443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Back-translation (BT) of target monolingual corpora is a widely used data augmentation strategy for neural machine translation (NMT), especially for low-resource language pairs. To improve effectiveness of the available BT data, we introduce HintedBT -- a family of techniques which provides hints (through tags) to the encoder and decoder. First, we propose a novel method of using both high and low quality BT data by providing hints (as source tags on the encoder) to the model about the quality of each source-target pair. We don't filter out low quality data but instead show that these hints en","authors_text":"Abhirut Gupta, Aravindan Raghuveer, Melvin Johnson, Sahana Ramnath","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T17:43:20Z","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04443","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:d5e8fe3e489124253f677e1164c83ff8fe932d670f2649dc32272bbc05d75414","target":"record","created_at":"2026-07-05T03:12:58Z","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":"e04af3a6572217061d4501515c2d10d7ae05a43ba587f711e30af9fc39e9f486","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T17:43:20Z","title_canon_sha256":"59acd967ba7e58b50b221088728e8dc1a78da04d36f63ec24b2d0545ee30aaac"},"schema_version":"1.0","source":{"id":"2109.04443","kind":"arxiv","version":1}},"canonical_sha256":"45b42878b3a48f20760e09199480fe2ef834bd632cf6d4ac6db1e136c462aaf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45b42878b3a48f20760e09199480fe2ef834bd632cf6d4ac6db1e136c462aaf6","first_computed_at":"2026-07-05T03:12:58.550195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:58.550195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OiYgrukAaap2wgl+qqYoKxsAitnrpaMhVaj/mkDeXEXMqU/RxpdPjmsEgfg6m5bhvt7XtnURTBM1fVsMwDuIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:58.550635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e8fe3e489124253f677e1164c83ff8fe932d670f2649dc32272bbc05d75414","sha256:eb943ce6d7e8e275e88eebbf40a123ec8528976f8dbb08f043c6ff031a9e2bb3"],"state_sha256":"c7dd06b85f9e50e6e4268a455c42789de46e12c0b9fbe70314137b4f71fd8170"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZO0+Z97Q6vu9TQAD7gDh4SjnPysbkV13EwuTRbsI1Y75ory/PE+dib+zjW0jL9VwNNjsG88eveZxU9S2ASeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:08:09.301391Z","bundle_sha256":"d22d0cf976dde6fb9101368cbaee35e9cd9f1699992e7d93f2dae04dc7e0625a"}}