{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QLFCF7JLNHW52O4SIUTLJ3SAZ4","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":"c16936a47ec347a8b152934155952456e7f4513e8f8d21752a6c2a4ef3c3dafd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T11:39:33Z","title_canon_sha256":"94a7f582b751611babdabd2b94d1643c05c27bfaeb72a1ac634db1c16a0ace76"},"schema_version":"1.0","source":{"id":"2104.08826","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08826","created_at":"2026-07-05T03:33:05Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08826v2","created_at":"2026-07-05T03:33:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08826","created_at":"2026-07-05T03:33:05Z"},{"alias_kind":"pith_short_12","alias_value":"QLFCF7JLNHW5","created_at":"2026-07-05T03:33:05Z"},{"alias_kind":"pith_short_16","alias_value":"QLFCF7JLNHW52O4S","created_at":"2026-07-05T03:33:05Z"},{"alias_kind":"pith_short_8","alias_value":"QLFCF7JL","created_at":"2026-07-05T03:33:05Z"}],"graph_snapshots":[{"event_id":"sha256:51b41c9d1f739de0ddd0c59b78f0a755f5eccaceb23319877fbcc8d528b8754c","target":"graph","created_at":"2026-07-05T03:33:05Z","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/2104.08826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them to be controlled via natural text prompts. Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability. This paper proposes a novel data augmentation technique that leverages large-scale language models to generate realistic text samples from a mixture of real samples. We also propose utilizing soft-labels predicted by the language models, effectively distilling knowledge from the large-scale language models and creating textual","authors_text":"Dongju Park, Jaewook Kang, Kang Min Yoo, Sang-Woo Lee, Woomyeong Park","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T11:39:33Z","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08826","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:f644fd4e7e7650bae5ac172140f4799363e84e6e782d5d85be341338e0352818","target":"record","created_at":"2026-07-05T03:33:05Z","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":"c16936a47ec347a8b152934155952456e7f4513e8f8d21752a6c2a4ef3c3dafd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T11:39:33Z","title_canon_sha256":"94a7f582b751611babdabd2b94d1643c05c27bfaeb72a1ac634db1c16a0ace76"},"schema_version":"1.0","source":{"id":"2104.08826","kind":"arxiv","version":2}},"canonical_sha256":"82ca22fd2b69eddd3b924526b4ee40cf2a54c1a3f25b7a70edf2a45679d6eab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82ca22fd2b69eddd3b924526b4ee40cf2a54c1a3f25b7a70edf2a45679d6eab2","first_computed_at":"2026-07-05T03:33:05.109680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:05.109680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ATGmUS0pitH9e1pItmIE9T3CkBndL7bjfHzN+0E8Sgwm6xV/7DEdhX7VwH8AGM8q94kuodm3ZLZW3GN+sNXBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:05.110199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08826","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f644fd4e7e7650bae5ac172140f4799363e84e6e782d5d85be341338e0352818","sha256:51b41c9d1f739de0ddd0c59b78f0a755f5eccaceb23319877fbcc8d528b8754c"],"state_sha256":"fcd5639c06673452d414f2a3a21ba0cfb9355eac69c00bab53c36340e3c48ba0"}