{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LQSKJEQDMQ47FIBVHHTMBHK5YN","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":"ce9547463c5e8e9e6af993d529e609959a5506eb71f0207c50fcd4ec44953305","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T17:30:08Z","title_canon_sha256":"018f5a83ac9a3243d463a8458f7b7c9db48e1c18a7cb0a94b2a237ff9d71b845"},"schema_version":"1.0","source":{"id":"2410.10756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10756","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10756v1","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10756","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"LQSKJEQDMQ47","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"LQSKJEQDMQ47FIBV","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"LQSKJEQD","created_at":"2026-07-05T09:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:9b60f2f10c3336ce67d144bc10729e265b52ce53eda59fdd08856eacf478a22d","target":"graph","created_at":"2026-07-05T09:20:20Z","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/2410.10756/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 used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for classifier fine-tuning. Existing works on augmentation leverage the few-shot scenarios, where samples are given to LLMs as part of prompts, leading to better augmentations. Yet, the samples are mostly selected randomly and a comprehensive overview of the effects of other (more ``informed'') sample selection strategies is lacking. In this work, we compare sample selection strategies existing in few-shot learning literature and in","authors_text":"Branislav Pecher, Ivan Srba, Jakub Simko, Jan Cegin, Maria Bielikova, Peter Brusilovsky","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T17:30:08Z","title":"Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10756","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":"sha256:4125bad73578076c1065298d6b99ded5ae1430613abc2cd7754e484b4a930fae","target":"record","created_at":"2026-07-05T09:20:20Z","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":"ce9547463c5e8e9e6af993d529e609959a5506eb71f0207c50fcd4ec44953305","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T17:30:08Z","title_canon_sha256":"018f5a83ac9a3243d463a8458f7b7c9db48e1c18a7cb0a94b2a237ff9d71b845"},"schema_version":"1.0","source":{"id":"2410.10756","kind":"arxiv","version":1}},"canonical_sha256":"5c24a492036439f2a03539e6c09d5dc34f046d86c3372cbfa24c56fb1ee4b118","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c24a492036439f2a03539e6c09d5dc34f046d86c3372cbfa24c56fb1ee4b118","first_computed_at":"2026-07-05T09:20:20.578429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:20.578429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnkDAXCVipDjkXeqjF/UPFVWwX7h6g7qLe+mKQF7cS55MUuVE5SCYFxE0DmN/anZ58kdnsIcUrbQY6UJP+nUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:20.578908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4125bad73578076c1065298d6b99ded5ae1430613abc2cd7754e484b4a930fae","sha256:9b60f2f10c3336ce67d144bc10729e265b52ce53eda59fdd08856eacf478a22d"],"state_sha256":"9e7064afff5c1bf9bca2c0d0ac60b61e4f3a52830da576937eb2d662a695faa5"}