{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AWFOINRCWA7ZBGKQCLA74SD7ZD","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":"3abb25679c93f26b6b44d54b5dd8e437cecdd60c531282eb988d4ad2d8e526dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T13:01:42Z","title_canon_sha256":"02c2176fca2d64e51a1a69ae3bc0eded3542f32a83455f915e6d1a27bf638c3e"},"schema_version":"1.0","source":{"id":"2408.16502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16502","created_at":"2026-07-05T09:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16502v1","created_at":"2026-07-05T09:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16502","created_at":"2026-07-05T09:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"AWFOINRCWA7Z","created_at":"2026-07-05T09:00:42Z"},{"alias_kind":"pith_short_16","alias_value":"AWFOINRCWA7ZBGKQ","created_at":"2026-07-05T09:00:42Z"},{"alias_kind":"pith_short_8","alias_value":"AWFOINRC","created_at":"2026-07-05T09:00:42Z"}],"graph_snapshots":[{"event_id":"sha256:1837bf34671b6e296e1f413340a7a0c1faead85c4aa5208cf041f102961f3d87","target":"graph","created_at":"2026-07-05T09:00:42Z","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/2408.16502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The generative large language models (LLMs) are increasingly being used for data augmentation tasks, where text samples are LLM-paraphrased and then used for classifier fine-tuning. However, a research that would confirm a clear cost-benefit advantage of LLMs over more established augmentation methods is largely missing. To study if (and when) is the LLM-based augmentation advantageous, we compared the effects of recent LLM augmentation methods with established ones on 6 datasets, 3 classifiers and 2 fine-tuning methods. We also varied the number of seeds and collected samples to better explor","authors_text":"Jakub Simko, Jan Cegin, Peter Brusilovsky","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T13:01:42Z","title":"LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16502","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":"sha256:8a1a97e4e56adf8cfe66b034683cb6fbd95e2e8f6a9b498b663eee6b74a8b374","target":"record","created_at":"2026-07-05T09:00:42Z","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":"3abb25679c93f26b6b44d54b5dd8e437cecdd60c531282eb988d4ad2d8e526dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T13:01:42Z","title_canon_sha256":"02c2176fca2d64e51a1a69ae3bc0eded3542f32a83455f915e6d1a27bf638c3e"},"schema_version":"1.0","source":{"id":"2408.16502","kind":"arxiv","version":1}},"canonical_sha256":"058ae43622b03f90995012c1fe487fc8d7caa26aa84b1c9956307e455c75d851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"058ae43622b03f90995012c1fe487fc8d7caa26aa84b1c9956307e455c75d851","first_computed_at":"2026-07-05T09:00:42.476841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:42.476841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u7qE/XODobhrT0xyJKpZLJEe7cOXf5KqVxmlT/29swHoLDBzKwJ6j6zrXLFQVcxSSSRAUw5I1euRVYBGPlmPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:42.477233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1a97e4e56adf8cfe66b034683cb6fbd95e2e8f6a9b498b663eee6b74a8b374","sha256:1837bf34671b6e296e1f413340a7a0c1faead85c4aa5208cf041f102961f3d87"],"state_sha256":"b6bef9181d78bfd064c6c3157b9aed08aef91796b9c6aede0c131a1f66addc08"}