{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QLFCF7JLNHW52O4SIUTLJ3SAZ4","short_pith_number":"pith:QLFCF7JL","schema_version":"1.0","canonical_sha256":"82ca22fd2b69eddd3b924526b4ee40cf2a54c1a3f25b7a70edf2a45679d6eab2","source":{"kind":"arxiv","id":"2104.08826","version":2},"attestation_state":"computed","paper":{"title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongju Park, Jaewook Kang, Kang Min Yoo, Sang-Woo Lee, Woomyeong Park","submitted_at":"2021-04-18T11:39:33Z","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"},"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":"2104.08826","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T11:39:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94a7f582b751611babdabd2b94d1643c05c27bfaeb72a1ac634db1c16a0ace76","abstract_canon_sha256":"c16936a47ec347a8b152934155952456e7f4513e8f8d21752a6c2a4ef3c3dafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:05.110199Z","signature_b64":"ATGmUS0pitH9e1pItmIE9T3CkBndL7bjfHzN+0E8Sgwm6xV/7DEdhX7VwH8AGM8q94kuodm3ZLZW3GN+sNXBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ca22fd2b69eddd3b924526b4ee40cf2a54c1a3f25b7a70edf2a45679d6eab2","last_reissued_at":"2026-07-05T03:33:05.109680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:05.109680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongju Park, Jaewook Kang, Kang Min Yoo, Sang-Woo Lee, Woomyeong Park","submitted_at":"2021-04-18T11:39:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08826","kind":"arxiv","version":2},"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/2104.08826/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":"2104.08826","created_at":"2026-07-05T03:33:05.109745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08826v2","created_at":"2026-07-05T03:33:05.109745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08826","created_at":"2026-07-05T03:33:05.109745+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLFCF7JLNHW5","created_at":"2026-07-05T03:33:05.109745+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLFCF7JLNHW52O4S","created_at":"2026-07-05T03:33:05.109745+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLFCF7JL","created_at":"2026-07-05T03:33:05.109745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.06226","citing_title":"No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4","json":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4.json","graph_json":"https://pith.science/api/pith-number/QLFCF7JLNHW52O4SIUTLJ3SAZ4/graph.json","events_json":"https://pith.science/api/pith-number/QLFCF7JLNHW52O4SIUTLJ3SAZ4/events.json","paper":"https://pith.science/paper/QLFCF7JL"},"agent_actions":{"view_html":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4","download_json":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4.json","view_paper":"https://pith.science/paper/QLFCF7JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08826&json=true","fetch_graph":"https://pith.science/api/pith-number/QLFCF7JLNHW52O4SIUTLJ3SAZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/QLFCF7JLNHW52O4SIUTLJ3SAZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4/action/storage_attestation","attest_author":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4/action/author_attestation","sign_citation":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4/action/citation_signature","submit_replication":"https://pith.science/pith/QLFCF7JLNHW52O4SIUTLJ3SAZ4/action/replication_record"}},"created_at":"2026-07-05T03:33:05.109745+00:00","updated_at":"2026-07-05T03:33:05.109745+00:00"}