{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NBIYSH2VMJJEENCRCE5JPACXSV","short_pith_number":"pith:NBIYSH2V","canonical_record":{"source":{"id":"2208.05909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-11T16:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"33de9ec73f922d76b6498d4315e2e55675f6ba4ddf03b0bda72ad2de0fcb3bb5","abstract_canon_sha256":"f627f304f165c009cb8eb3c9e7fb161ca588153943e95ab24437f1ab9089a9e0"},"schema_version":"1.0"},"canonical_sha256":"6851891f556252423451113a97805795697a446ff172f19644d7864db24786b9","source":{"kind":"arxiv","id":"2208.05909","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05909","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05909v1","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05909","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"NBIYSH2VMJJE","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_16","alias_value":"NBIYSH2VMJJEENCR","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_8","alias_value":"NBIYSH2V","created_at":"2026-07-05T04:57:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NBIYSH2VMJJEENCRCE5JPACXSV","target":"record","payload":{"canonical_record":{"source":{"id":"2208.05909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-11T16:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"33de9ec73f922d76b6498d4315e2e55675f6ba4ddf03b0bda72ad2de0fcb3bb5","abstract_canon_sha256":"f627f304f165c009cb8eb3c9e7fb161ca588153943e95ab24437f1ab9089a9e0"},"schema_version":"1.0"},"canonical_sha256":"6851891f556252423451113a97805795697a446ff172f19644d7864db24786b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:26.875196Z","signature_b64":"p21D3Po+TdGYEPdo9yR9Lt7FK2GQjIebJH93w/5eSf9rNC/Jue2ptfdPZRu1bv/Y95+kao+yNuzogpi5eDDADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6851891f556252423451113a97805795697a446ff172f19644d7864db24786b9","last_reissued_at":"2026-07-05T04:57:26.874767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:26.874767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.05909","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":"2026-07-05T04:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTV5ftALBekWxrf4fB1+P+x2hlIXvEepr7KK7QpOp454VFWkldolattWC+iYbExVssLOBurIkwUa2iXXJ20yCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:43:39.940934Z"},"content_sha256":"02983e489b377bc5b974be485c32c7a4ae61e0f0a00f86c9373908bf8be79c2e","schema_version":"1.0","event_id":"sha256:02983e489b377bc5b974be485c32c7a4ae61e0f0a00f86c9373908bf8be79c2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NBIYSH2VMJJEENCRCE5JPACXSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Specific Text Generation for Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Way, John D. Kelleher, Rejwanul Haque, Yasmin Moslem","submitted_at":"2022-08-11T16:22:16Z","abstract_excerpt":"Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such scenarios where there is insufficient in-domain data to fine-tune Machine Translation (MT) models, producing translations that are consistent with the relevant context is challenging. In this work, we propose a novel approach to domain adaptation leveraging state-of-the-art pretrained language models (LMs) for domain-specific data augmentation for MT, simulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05909","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/2208.05909/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":"2026-07-05T04:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNh0GEcDch9MNDYgkz5JWPsLKpzhWojFKqKZd7X6vA2y8gtu4b2/czcgqePenS7d3eMZyrdvoUy7eQmYEAuGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:43:39.941281Z"},"content_sha256":"7dd962905a420c65df84d6fada80a72a5f54250c29b02adfbc22d2b1ab5f2187","schema_version":"1.0","event_id":"sha256:7dd962905a420c65df84d6fada80a72a5f54250c29b02adfbc22d2b1ab5f2187"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBIYSH2VMJJEENCRCE5JPACXSV/bundle.json","state_url":"https://pith.science/pith/NBIYSH2VMJJEENCRCE5JPACXSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBIYSH2VMJJEENCRCE5JPACXSV/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":"2026-08-22T00:43:39Z","links":{"resolver":"https://pith.science/pith/NBIYSH2VMJJEENCRCE5JPACXSV","bundle":"https://pith.science/pith/NBIYSH2VMJJEENCRCE5JPACXSV/bundle.json","state":"https://pith.science/pith/NBIYSH2VMJJEENCRCE5JPACXSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBIYSH2VMJJEENCRCE5JPACXSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NBIYSH2VMJJEENCRCE5JPACXSV","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":"f627f304f165c009cb8eb3c9e7fb161ca588153943e95ab24437f1ab9089a9e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-11T16:22:16Z","title_canon_sha256":"33de9ec73f922d76b6498d4315e2e55675f6ba4ddf03b0bda72ad2de0fcb3bb5"},"schema_version":"1.0","source":{"id":"2208.05909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05909","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05909v1","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05909","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"NBIYSH2VMJJE","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_16","alias_value":"NBIYSH2VMJJEENCR","created_at":"2026-07-05T04:57:26Z"},{"alias_kind":"pith_short_8","alias_value":"NBIYSH2V","created_at":"2026-07-05T04:57:26Z"}],"graph_snapshots":[{"event_id":"sha256:7dd962905a420c65df84d6fada80a72a5f54250c29b02adfbc22d2b1ab5f2187","target":"graph","created_at":"2026-07-05T04:57:26Z","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/2208.05909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such scenarios where there is insufficient in-domain data to fine-tune Machine Translation (MT) models, producing translations that are consistent with the relevant context is challenging. In this work, we propose a novel approach to domain adaptation leveraging state-of-the-art pretrained language models (LMs) for domain-specific data augmentation for MT, simulat","authors_text":"Andy Way, John D. Kelleher, Rejwanul Haque, Yasmin Moslem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-11T16:22:16Z","title":"Domain-Specific Text Generation for Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05909","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":"sha256:02983e489b377bc5b974be485c32c7a4ae61e0f0a00f86c9373908bf8be79c2e","target":"record","created_at":"2026-07-05T04:57:26Z","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":"f627f304f165c009cb8eb3c9e7fb161ca588153943e95ab24437f1ab9089a9e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-11T16:22:16Z","title_canon_sha256":"33de9ec73f922d76b6498d4315e2e55675f6ba4ddf03b0bda72ad2de0fcb3bb5"},"schema_version":"1.0","source":{"id":"2208.05909","kind":"arxiv","version":1}},"canonical_sha256":"6851891f556252423451113a97805795697a446ff172f19644d7864db24786b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6851891f556252423451113a97805795697a446ff172f19644d7864db24786b9","first_computed_at":"2026-07-05T04:57:26.874767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:26.874767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p21D3Po+TdGYEPdo9yR9Lt7FK2GQjIebJH93w/5eSf9rNC/Jue2ptfdPZRu1bv/Y95+kao+yNuzogpi5eDDADg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:26.875196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.05909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02983e489b377bc5b974be485c32c7a4ae61e0f0a00f86c9373908bf8be79c2e","sha256:7dd962905a420c65df84d6fada80a72a5f54250c29b02adfbc22d2b1ab5f2187"],"state_sha256":"7076f7569f3372af4c12d67d17bbc6aa6fb8bb4bca61b8b3ef4d5f8f0ef90b3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQqRizumsunUARJQ3eRqvnV5pM5aW1deuTsnILEhmnhMLw94p4Sc0hZEcVXp1gI+i5a1bBcxk+jlRHE5HdCNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:43:39.944740Z","bundle_sha256":"52e91e4461d3caae63427e27b79926e11a5f2c092cc38007d1927ebf3ed3568c"}}