{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PVCSURAUP4FAJWUCFQUJVVAMEY","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":"5415d649d1d32b005992100d8c583695a06919c244d5d046673dfb39b31ddd5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T12:10:03Z","title_canon_sha256":"7ba6f25c736cf423bbe312d02ee39cc9e4dd23028e7bf54e125ba2f66ef6d99e"},"schema_version":"1.0","source":{"id":"2111.09064","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09064","created_at":"2026-07-05T05:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09064v2","created_at":"2026-07-05T05:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09064","created_at":"2026-07-05T05:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"PVCSURAUP4FA","created_at":"2026-07-05T05:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"PVCSURAUP4FAJWUC","created_at":"2026-07-05T05:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"PVCSURAU","created_at":"2026-07-05T05:31:11Z"}],"graph_snapshots":[{"event_id":"sha256:80bbe1ecfbe3499eeb5d46ec19a9e5581d392d9ae9ebf9f9ab529e023a808535","target":"graph","created_at":"2026-07-05T05:31:11Z","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/2111.09064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant gains across different NLP tasks. However, their applicability to data augmentation for text classification tasks in few-shot settings have not been fully explored, especially for specialised domains. In this paper, we leverage GPT-2 (Radford A et al, 2019) for generating artificial training instances in order to improve classification performance. Our aim is","authors_text":"Aleksandra Edwards, Alun Preece, Asahi Ushio, H\\'el\\`ene De Ribaupierre, Jose Camacho-Collados","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T12:10:03Z","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09064","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:b585b7dee65ff6469bc2684acc1105d076707a94670ca81087c525cef8929fe5","target":"record","created_at":"2026-07-05T05:31:11Z","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":"5415d649d1d32b005992100d8c583695a06919c244d5d046673dfb39b31ddd5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-17T12:10:03Z","title_canon_sha256":"7ba6f25c736cf423bbe312d02ee39cc9e4dd23028e7bf54e125ba2f66ef6d99e"},"schema_version":"1.0","source":{"id":"2111.09064","kind":"arxiv","version":2}},"canonical_sha256":"7d452a44147f0a04da822c289ad40c2638df18ebf733b74a597a3daf73120f07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d452a44147f0a04da822c289ad40c2638df18ebf733b74a597a3daf73120f07","first_computed_at":"2026-07-05T05:31:11.810059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:11.810059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KJqfTSZAFo03Q2YktP1pNpSYkt7Ql96mDpcbaRPQGKVXn+gEIJ9nYbGLTY69E5Aml4/VPeGdjf/XAgHWJqRUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:11.810459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09064","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b585b7dee65ff6469bc2684acc1105d076707a94670ca81087c525cef8929fe5","sha256:80bbe1ecfbe3499eeb5d46ec19a9e5581d392d9ae9ebf9f9ab529e023a808535"],"state_sha256":"65185837376133d5046f2253c977858a8bee29f6ebda9ee0be8b2a372b3a34df"}