{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K5VPJWWRHZESJRBL24S6S4EADA","short_pith_number":"pith:K5VPJWWR","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"},"canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","source":{"kind":"arxiv","id":"2310.01119","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01119","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01119v2","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01119","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"K5VPJWWRHZES","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"K5VPJWWRHZESJRBL","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"K5VPJWWR","created_at":"2026-07-05T07:30:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K5VPJWWRHZESJRBL24S6S4EADA","target":"record","payload":{"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"},"canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","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"},"source_kind":"arxiv","source_id":"2310.01119","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nx0Efe4uwoEtgh533xVp8//zTuMAV7zs2cRKSLjjCQyh9S8Gboqp+t3eEDBn7zWrEDdiHdVL87ggs/sopTjnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:40:03.004431Z"},"content_sha256":"8b3c2bfbb1c8943213acc4b3fad5aa9634f15a5bdd5d81eb1ab287c1f250c2ff","schema_version":"1.0","event_id":"sha256:8b3c2bfbb1c8943213acc4b3fad5aa9634f15a5bdd5d81eb1ab287c1f250c2ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K5VPJWWRHZESJRBL24S6S4EADA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htOHlz74sIvH7DYH8SH1GwiNTyZOgDG0YvidoJvFAremzgUUdiBFmePVJEXEEgfOiweQyBdXNr6hfFzcV9DZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:40:03.004943Z"},"content_sha256":"efa4b857269629448b17f0b5ec0a83fad3ddd8709876c7c01d94b5e53fc335ac","schema_version":"1.0","event_id":"sha256:efa4b857269629448b17f0b5ec0a83fad3ddd8709876c7c01d94b5e53fc335ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/bundle.json","state_url":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5VPJWWRHZESJRBL24S6S4EADA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:40:03Z","links":{"resolver":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA","bundle":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/bundle.json","state":"https://pith.science/pith/K5VPJWWRHZESJRBL24S6S4EADA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5VPJWWRHZESJRBL24S6S4EADA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K5VPJWWRHZESJRBL24S6S4EADA","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":"5ca3ccbcbf3a18e25ffffa52e88940c215df081fe5d6752a65544bdef83d625d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T11:49:05Z","title_canon_sha256":"b2c4c425dedf2c682793c8be4cd95bc9de60876db2f64205d2f7ac658d21c9b7"},"schema_version":"1.0","source":{"id":"2310.01119","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01119","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01119v2","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01119","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"K5VPJWWRHZES","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"K5VPJWWRHZESJRBL","created_at":"2026-07-05T07:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"K5VPJWWR","created_at":"2026-07-05T07:30:54Z"}],"graph_snapshots":[{"event_id":"sha256:efa4b857269629448b17f0b5ec0a83fad3ddd8709876c7c01d94b5e53fc335ac","target":"graph","created_at":"2026-07-05T07:30:54Z","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/2310.01119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jean Kaddour, Qi Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T11:49:05Z","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01119","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":"sha256:8b3c2bfbb1c8943213acc4b3fad5aa9634f15a5bdd5d81eb1ab287c1f250c2ff","target":"record","created_at":"2026-07-05T07:30:54Z","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":"5ca3ccbcbf3a18e25ffffa52e88940c215df081fe5d6752a65544bdef83d625d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T11:49:05Z","title_canon_sha256":"b2c4c425dedf2c682793c8be4cd95bc9de60876db2f64205d2f7ac658d21c9b7"},"schema_version":"1.0","source":{"id":"2310.01119","kind":"arxiv","version":2}},"canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"576af4dad13e4924c42bd725e970801834ccc1d227e2d8eaef89c1fa193478c8","first_computed_at":"2026-07-05T07:30:54.335298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:54.335298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LiCgWRnwOz6R20RtB8d/F4ZmntwhDUFm/614Y+i5XUqB2DBND5371seyqz/Y5fONJYZHrq2AnwkfVw9tM0KaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:54.335800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01119","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b3c2bfbb1c8943213acc4b3fad5aa9634f15a5bdd5d81eb1ab287c1f250c2ff","sha256:efa4b857269629448b17f0b5ec0a83fad3ddd8709876c7c01d94b5e53fc335ac"],"state_sha256":"44b1d771ef59f0735069b1afa8d0ddd1fab74b90a54896dd3e7b619120fcb097"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdlRe428RjmLD1VVIA2Lu0Pz5jzOrZG4por/wBy522Dq8aTi1GriMpgn8C92B20CN4ab9064jtgeOwTIpy02BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:40:03.008917Z","bundle_sha256":"2b2ff5db0a9d75184a3c1b8ef433b72430de0501550ce55b1f4d9341fafe6681"}}