{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K5VPJWWRHZESJRBL24S6S4EADA","short_pith_number":"pith:K5VPJWWR","schema_version":"1.0","canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","source":{"kind":"arxiv","id":"2310.01119","version":2},"attestation_state":"computed","paper":{"title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jean Kaddour, Qi Liu","submitted_at":"2023-10-02T11:49:05Z","abstract_excerpt":"The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively, smaller models can solve specific tasks if fine-tuned with enough labeled examples. These examples, however, are expensive to obtain. In pursuit of the best of both worlds, we study synthetic data generation of fine-tuning training data via fine-tuned teacher LLMs to improve the downstream performance of much smaller models. In four text classification and "},"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":"2310.01119","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T11:49:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2c4c425dedf2c682793c8be4cd95bc9de60876db2f64205d2f7ac658d21c9b7","abstract_canon_sha256":"5ca3ccbcbf3a18e25ffffa52e88940c215df081fe5d6752a65544bdef83d625d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:54.335800Z","signature_b64":"LiCgWRnwOz6R20RtB8d/F4ZmntwhDUFm/614Y+i5XUqB2DBND5371seyqz/Y5fONJYZHrq2AnwkfVw9tM0KaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","last_reissued_at":"2026-07-05T07:30:54.335298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:54.335298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jean Kaddour, Qi Liu","submitted_at":"2023-10-02T11:49:05Z","abstract_excerpt":"The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively, smaller models can solve specific tasks if fine-tuned with enough labeled examples. These examples, however, are expensive to obtain. In pursuit of the best of both worlds, we study synthetic data generation of fine-tuning training data via fine-tuned teacher LLMs to improve the downstream performance of much smaller models. In four text classification and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01119","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/2310.01119/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":"2310.01119","created_at":"2026-07-05T07:30:54.335383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01119v2","created_at":"2026-07-05T07:30:54.335383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01119","created_at":"2026-07-05T07:30:54.335383+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5VPJWWRHZES","created_at":"2026-07-05T07:30:54.335383+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5VPJWWRHZESJRBL","created_at":"2026-07-05T07:30:54.335383+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5VPJWWR","created_at":"2026-07-05T07:30:54.335383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08515","citing_title":"The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA","json":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA.json","graph_json":"https://pith.science/api/pith-number/K5VPJWWRHZESJRBL24S6S4EADA/graph.json","events_json":"https://pith.science/api/pith-number/K5VPJWWRHZESJRBL24S6S4EADA/events.json","paper":"https://pith.science/paper/K5VPJWWR"},"agent_actions":{"view_html":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA","download_json":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA.json","view_paper":"https://pith.science/paper/K5VPJWWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01119&json=true","fetch_graph":"https://pith.science/api/pith-number/K5VPJWWRHZESJRBL24S6S4EADA/graph.json","fetch_events":"https://pith.science/api/pith-number/K5VPJWWRHZESJRBL24S6S4EADA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/action/storage_attestation","attest_author":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/action/author_attestation","sign_citation":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/action/citation_signature","submit_replication":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/action/replication_record"}},"created_at":"2026-07-05T07:30:54.335383+00:00","updated_at":"2026-07-05T07:30:54.335383+00:00"}