{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AWFOINRCWA7ZBGKQCLA74SD7ZD","short_pith_number":"pith:AWFOINRC","schema_version":"1.0","canonical_sha256":"058ae43622b03f90995012c1fe487fc8d7caa26aa84b1c9956307e455c75d851","source":{"kind":"arxiv","id":"2408.16502","version":1},"attestation_state":"computed","paper":{"title":"LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jakub Simko, Jan Cegin, Peter Brusilovsky","submitted_at":"2024-08-29T13:01:42Z","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"},"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":"2408.16502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T13:01:42Z","cross_cats_sorted":[],"title_canon_sha256":"02c2176fca2d64e51a1a69ae3bc0eded3542f32a83455f915e6d1a27bf638c3e","abstract_canon_sha256":"3abb25679c93f26b6b44d54b5dd8e437cecdd60c531282eb988d4ad2d8e526dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:42.477233Z","signature_b64":"u7qE/XODobhrT0xyJKpZLJEe7cOXf5KqVxmlT/29swHoLDBzKwJ6j6zrXLFQVcxSSSRAUw5I1euRVYBGPlmPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058ae43622b03f90995012c1fe487fc8d7caa26aa84b1c9956307e455c75d851","last_reissued_at":"2026-07-05T09:00:42.476841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:42.476841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jakub Simko, Jan Cegin, Peter Brusilovsky","submitted_at":"2024-08-29T13:01:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16502","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/2408.16502/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":"2408.16502","created_at":"2026-07-05T09:00:42.476898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16502v1","created_at":"2026-07-05T09:00:42.476898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16502","created_at":"2026-07-05T09:00:42.476898+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWFOINRCWA7Z","created_at":"2026-07-05T09:00:42.476898+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWFOINRCWA7ZBGKQ","created_at":"2026-07-05T09:00:42.476898+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWFOINRC","created_at":"2026-07-05T09:00:42.476898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11285","citing_title":"AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models' Responses to Depression, Anxiety, and Stress Queries","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD","json":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD.json","graph_json":"https://pith.science/api/pith-number/AWFOINRCWA7ZBGKQCLA74SD7ZD/graph.json","events_json":"https://pith.science/api/pith-number/AWFOINRCWA7ZBGKQCLA74SD7ZD/events.json","paper":"https://pith.science/paper/AWFOINRC"},"agent_actions":{"view_html":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD","download_json":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD.json","view_paper":"https://pith.science/paper/AWFOINRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16502&json=true","fetch_graph":"https://pith.science/api/pith-number/AWFOINRCWA7ZBGKQCLA74SD7ZD/graph.json","fetch_events":"https://pith.science/api/pith-number/AWFOINRCWA7ZBGKQCLA74SD7ZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD/action/storage_attestation","attest_author":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD/action/author_attestation","sign_citation":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD/action/citation_signature","submit_replication":"https://pith.science/pith/AWFOINRCWA7ZBGKQCLA74SD7ZD/action/replication_record"}},"created_at":"2026-07-05T09:00:42.476898+00:00","updated_at":"2026-07-05T09:00:42.476898+00:00"}