{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6NTYE7PRHYFMDMDUBSF4LQJDH5","short_pith_number":"pith:6NTYE7PR","canonical_record":{"source":{"id":"2403.15042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"da02c7f73fa5ab1a5172a70d4504b927c9dfd47a08a234be2f09904b481af9ba","abstract_canon_sha256":"5b8d7e28e9fb18f3fe717987fa7be8f9372d371bd5f66d0ab60a804cf7ab47dc"},"schema_version":"1.0"},"canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","source":{"kind":"arxiv","id":"2403.15042","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15042","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15042v2","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15042","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"6NTYE7PRHYFM","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"6NTYE7PRHYFMDMDU","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"6NTYE7PR","created_at":"2026-07-05T08:43:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6NTYE7PRHYFMDMDUBSF4LQJDH5","target":"record","payload":{"canonical_record":{"source":{"id":"2403.15042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"da02c7f73fa5ab1a5172a70d4504b927c9dfd47a08a234be2f09904b481af9ba","abstract_canon_sha256":"5b8d7e28e9fb18f3fe717987fa7be8f9372d371bd5f66d0ab60a804cf7ab47dc"},"schema_version":"1.0"},"canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:27.334978Z","signature_b64":"jCo0r0FyJR2YHiPADPZO6SKBIBC1MzOyAdGklKvDQSEXGx+eSWrTfGD/7e5GGfEkflP8GuhIK/yW8gyHgIFdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","last_reissued_at":"2026-07-05T08:43:27.334512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:27.334512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.15042","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":"2026-07-05T08:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDXpvIoAXxi9MEGobJHPfQqu2R37EuX80vhgJzIfYvvv9cxE2R8pon8pQNtpzYLei0GiocoW3JZ8lECzKmCoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:30:57.315469Z"},"content_sha256":"0c6a2e207cebc6ba3e8f76c3d932cfec9097aaf77dff32393adb3db3fa1c4bcf","schema_version":"1.0","event_id":"sha256:0c6a2e207cebc6ba3e8f76c3d932cfec9097aaf77dff32393adb3db3fa1c4bcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6NTYE7PRHYFMDMDUBSF4LQJDH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Gholami, Gopala Anumanchipalli, Karttikeya Mangalam, Kurt Keutzer, Michael W. Mahoney, Nicholas Lee, Sehoon Kim, Sheng Shen, Thanakul Wattanawong","submitted_at":"2024-03-22T08:57:07Z","abstract_excerpt":"Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many of them are in the low-data regime, making fine-tuning challenging. To address this, we propose LLM2LLM, a targeted and iterative data augmentation strategy that uses a teacher LLM to enhance a small seed dataset by augmenting additional data that can be used for fine-tuning on a specific task. LLM2LLM (1) fine-tunes a baseline student LLM on the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15042","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/2403.15042/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":"2026-07-05T08:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZKxPO3/YTsK8j7X2DpqHPuoTP9SaG8ZwIg72MPWIFSg/hiM1YJxLQxagWN5jkKHRs5Ia44ATFSpW7o3ni3xRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:30:57.316464Z"},"content_sha256":"e38662bfa267348b45a9d866fdd02ac9e29d4c910814ac726a91033fe6e09a9d","schema_version":"1.0","event_id":"sha256:e38662bfa267348b45a9d866fdd02ac9e29d4c910814ac726a91033fe6e09a9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/bundle.json","state_url":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/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":"2026-08-08T21:30:57Z","links":{"resolver":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5","bundle":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/bundle.json","state":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6NTYE7PRHYFMDMDUBSF4LQJDH5","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":"5b8d7e28e9fb18f3fe717987fa7be8f9372d371bd5f66d0ab60a804cf7ab47dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","title_canon_sha256":"da02c7f73fa5ab1a5172a70d4504b927c9dfd47a08a234be2f09904b481af9ba"},"schema_version":"1.0","source":{"id":"2403.15042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15042","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15042v2","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15042","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"6NTYE7PRHYFM","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"6NTYE7PRHYFMDMDU","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"6NTYE7PR","created_at":"2026-07-05T08:43:27Z"}],"graph_snapshots":[{"event_id":"sha256:e38662bfa267348b45a9d866fdd02ac9e29d4c910814ac726a91033fe6e09a9d","target":"graph","created_at":"2026-07-05T08:43:27Z","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/2403.15042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many of them are in the low-data regime, making fine-tuning challenging. To address this, we propose LLM2LLM, a targeted and iterative data augmentation strategy that uses a teacher LLM to enhance a small seed dataset by augmenting additional data that can be used for fine-tuning on a specific task. LLM2LLM (1) fine-tunes a baseline student LLM on the i","authors_text":"Amir Gholami, Gopala Anumanchipalli, Karttikeya Mangalam, Kurt Keutzer, Michael W. Mahoney, Nicholas Lee, Sehoon Kim, Sheng Shen, Thanakul Wattanawong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15042","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":"sha256:0c6a2e207cebc6ba3e8f76c3d932cfec9097aaf77dff32393adb3db3fa1c4bcf","target":"record","created_at":"2026-07-05T08:43:27Z","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":"5b8d7e28e9fb18f3fe717987fa7be8f9372d371bd5f66d0ab60a804cf7ab47dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","title_canon_sha256":"da02c7f73fa5ab1a5172a70d4504b927c9dfd47a08a234be2f09904b481af9ba"},"schema_version":"1.0","source":{"id":"2403.15042","kind":"arxiv","version":2}},"canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","first_computed_at":"2026-07-05T08:43:27.334512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:27.334512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jCo0r0FyJR2YHiPADPZO6SKBIBC1MzOyAdGklKvDQSEXGx+eSWrTfGD/7e5GGfEkflP8GuhIK/yW8gyHgIFdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:27.334978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.15042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c6a2e207cebc6ba3e8f76c3d932cfec9097aaf77dff32393adb3db3fa1c4bcf","sha256:e38662bfa267348b45a9d866fdd02ac9e29d4c910814ac726a91033fe6e09a9d"],"state_sha256":"af090457755efde36a15d51403f7be55ebb0460a5dee7fdb0660758fb18733c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ee/S7+eELWbYNFZQ30fsAGtbJh+WuwwS2YBI0X3RfvOqMWUxfdm2NIaj+KoYddv7eAdBCF/SH9lAzdnrDLR1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:30:57.321608Z","bundle_sha256":"6900f83ab8e2a58bc05af150e2d394c63ad523dbcee6dbf32def99e9d3399e54"}}