{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DYEUYEGQLFCCXQVHA7342IQYFO","short_pith_number":"pith:DYEUYEGQ","schema_version":"1.0","canonical_sha256":"1e094c10d059442bc2a707f7cd22182ba698a026060819cf9b58c1a5bcd2953a","source":{"kind":"arxiv","id":"2307.05779","version":1},"attestation_state":"computed","paper":{"title":"Neural Machine Translation Data Generation and Augmentation using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Garrett Nicolai, Wayne Yang","submitted_at":"2023-07-11T20:15:47Z","abstract_excerpt":"Neural models have revolutionized the field of machine translation, but creating parallel corpora is expensive and time-consuming. We investigate an alternative to manual parallel corpora - hallucinated parallel corpora created by generative language models. Although these models are themselves trained on parallel data, they can leverage a multilingual vector space to create data, and may be able to supplement small manually-procured corpora. Our experiments highlight two key findings - despite a lack of diversity in their output, the hallucinated data improves the translation signal, even whe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.05779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T20:15:47Z","cross_cats_sorted":[],"title_canon_sha256":"d49c2f9783f2f01b3443dd0881e058363364b3895829f6f202a078470faf75c2","abstract_canon_sha256":"eb451a7b42b12c469b019e6129011eda3e3833f7eb0fbbc7da785de6650cec88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:12.314431Z","signature_b64":"t6xAZLcws5uURnIchg+Klcn9Km4aNZABQrmzFEQICy/Bt1puPENpsDYIohvfD1HZQni2+wDW1tP7K78JiV1ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e094c10d059442bc2a707f7cd22182ba698a026060819cf9b58c1a5bcd2953a","last_reissued_at":"2026-07-05T06:30:12.314053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:12.314053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Machine Translation Data Generation and Augmentation using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Garrett Nicolai, Wayne Yang","submitted_at":"2023-07-11T20:15:47Z","abstract_excerpt":"Neural models have revolutionized the field of machine translation, but creating parallel corpora is expensive and time-consuming. We investigate an alternative to manual parallel corpora - hallucinated parallel corpora created by generative language models. Although these models are themselves trained on parallel data, they can leverage a multilingual vector space to create data, and may be able to supplement small manually-procured corpora. Our experiments highlight two key findings - despite a lack of diversity in their output, the hallucinated data improves the translation signal, even whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05779","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/2307.05779/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.05779","created_at":"2026-07-05T06:30:12.314110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05779v1","created_at":"2026-07-05T06:30:12.314110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05779","created_at":"2026-07-05T06:30:12.314110+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYEUYEGQLFCC","created_at":"2026-07-05T06:30:12.314110+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYEUYEGQLFCCXQVH","created_at":"2026-07-05T06:30:12.314110+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYEUYEGQ","created_at":"2026-07-05T06:30:12.314110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO","json":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO.json","graph_json":"https://pith.science/api/pith-number/DYEUYEGQLFCCXQVHA7342IQYFO/graph.json","events_json":"https://pith.science/api/pith-number/DYEUYEGQLFCCXQVHA7342IQYFO/events.json","paper":"https://pith.science/paper/DYEUYEGQ"},"agent_actions":{"view_html":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO","download_json":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO.json","view_paper":"https://pith.science/paper/DYEUYEGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05779&json=true","fetch_graph":"https://pith.science/api/pith-number/DYEUYEGQLFCCXQVHA7342IQYFO/graph.json","fetch_events":"https://pith.science/api/pith-number/DYEUYEGQLFCCXQVHA7342IQYFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO/action/storage_attestation","attest_author":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO/action/author_attestation","sign_citation":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO/action/citation_signature","submit_replication":"https://pith.science/pith/DYEUYEGQLFCCXQVHA7342IQYFO/action/replication_record"}},"created_at":"2026-07-05T06:30:12.314110+00:00","updated_at":"2026-07-05T06:30:12.314110+00:00"}