{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NGK3NLJDJ35ILCEIAVRSIWIJVO","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":"ca36dd5b7034d8614cb38ff239e37ada7beca988fa51381992612eda482fffe7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T02:12:58Z","title_canon_sha256":"eedfc96db759e9a3d9db4a4274369408b7faedf8a03663aebd6bfd75b8895c33"},"schema_version":"1.0","source":{"id":"2307.16833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16833","created_at":"2026-07-05T07:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16833v2","created_at":"2026-07-05T07:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16833","created_at":"2026-07-05T07:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"NGK3NLJDJ35I","created_at":"2026-07-05T07:11:58Z"},{"alias_kind":"pith_short_16","alias_value":"NGK3NLJDJ35ILCEI","created_at":"2026-07-05T07:11:58Z"},{"alias_kind":"pith_short_8","alias_value":"NGK3NLJD","created_at":"2026-07-05T07:11:58Z"}],"graph_snapshots":[{"event_id":"sha256:9b6ae16071f166faeecb388a318a6f76b7dabb0a3e43d02a5ae323c0875d6973","target":"graph","created_at":"2026-07-05T07:11:58Z","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/2307.16833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by generating synthetic data instead of collecting new ones. We explore prompt-based data augmentation approaches that leverage large-scale language models such as ChatGPT. To create a synthetic parallel corpus, we compare 3 methods using different prompts. We employ two assessment metrics to measure the diversity of the generated synthetic data. This approach requir","authors_text":"Seokjin Oh, Su Ah Lee, Woohwan Jung","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T02:12:58Z","title":"Data Augmentation for Neural Machine Translation using Generative Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16833","kind":"arxiv","version":2},"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":"sha256:53141e062068f91589a57171f59027fae8dd5d063a4da24318c576843046aa1e","target":"record","created_at":"2026-07-05T07:11:58Z","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":"ca36dd5b7034d8614cb38ff239e37ada7beca988fa51381992612eda482fffe7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T02:12:58Z","title_canon_sha256":"eedfc96db759e9a3d9db4a4274369408b7faedf8a03663aebd6bfd75b8895c33"},"schema_version":"1.0","source":{"id":"2307.16833","kind":"arxiv","version":2}},"canonical_sha256":"6995b6ad234efa8588880563245909ab936a7f9ca177da408e6b09f805fe3966","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6995b6ad234efa8588880563245909ab936a7f9ca177da408e6b09f805fe3966","first_computed_at":"2026-07-05T07:11:58.575969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:58.575969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zcpFBCIHr5fFiWWnlNb2HZ28iBeetfc7VmgwAhpGgF8nQELfnYKZhyq97YOqoxicUSRE49d1MIoi03rdaOQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:58.576400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53141e062068f91589a57171f59027fae8dd5d063a4da24318c576843046aa1e","sha256:9b6ae16071f166faeecb388a318a6f76b7dabb0a3e43d02a5ae323c0875d6973"],"state_sha256":"f6f4a71bf4b6542e262a16af8ffaa6acd9b60f531ae5a9852861d4c4908eecf5"}