{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GEU222O7SXDZYARW4D5YUWENE2","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":"3bc03975386e71e0025fef44ebc22a3607b2c6e38d6d9ec4b92f8709203f953c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T17:15:32Z","title_canon_sha256":"fb7f03ec32330c778ee3e4ab812c4ef034517f1f40f14cfa42eddc239fe446d1"},"schema_version":"1.0","source":{"id":"2404.14361","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14361","created_at":"2026-07-05T08:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14361v3","created_at":"2026-07-05T08:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14361","created_at":"2026-07-05T08:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"GEU222O7SXDZ","created_at":"2026-07-05T08:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"GEU222O7SXDZYARW","created_at":"2026-07-05T08:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"GEU222O7","created_at":"2026-07-05T08:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:c53a2f07960d4a9da2dc3b74df57f03344464b42d63e96b2f246cb587e3a6d76","target":"graph","created_at":"2026-07-05T08:12:50Z","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/2404.14361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in large language models, building dependable and deployable NLP models typically requires abundant, high-quality training data. However, task-specific data is not available for many use cases, and manually curating task-specific data is labor-intensive. Recent work has studied prompt-driven synthetic data generation using large language models, but these generated datasets tend to lack complexity and diversity. To address these limitations, we introduce a method, DataTune, to make better use of existing, publicly available datasets to improve automatic dataset generati","authors_text":"Graham Neubig, Ritu Gala, Saumya Gandhi, Tongshuang Wu, Vijay Viswanathan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T17:15:32Z","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14361","kind":"arxiv","version":3},"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":"sha256:3431a1a9d7e1c9ab1097b2b9f1aa563ffe5c4860a308ccf330d7995a0303b2e6","target":"record","created_at":"2026-07-05T08:12:50Z","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":"3bc03975386e71e0025fef44ebc22a3607b2c6e38d6d9ec4b92f8709203f953c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T17:15:32Z","title_canon_sha256":"fb7f03ec32330c778ee3e4ab812c4ef034517f1f40f14cfa42eddc239fe446d1"},"schema_version":"1.0","source":{"id":"2404.14361","kind":"arxiv","version":3}},"canonical_sha256":"3129ad69df95c79c0236e0fb8a588d26ba870397125f79dc6000d65ee99f35b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3129ad69df95c79c0236e0fb8a588d26ba870397125f79dc6000d65ee99f35b0","first_computed_at":"2026-07-05T08:12:50.347614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:50.347614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVm1WTau9w3Yjq5xhmR8eOcEU+8CgTVgBAybMjqUVZqbUH7N4HGTW93C2o5Z/yx3mBVbXtyqQQ6hx9Rl1WSbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:50.348011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14361","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3431a1a9d7e1c9ab1097b2b9f1aa563ffe5c4860a308ccf330d7995a0303b2e6","sha256:c53a2f07960d4a9da2dc3b74df57f03344464b42d63e96b2f246cb587e3a6d76"],"state_sha256":"4a760372c974e4c37ebe48d8ad8589b50180666a6e0f546dd049956481dc9a7e"}