{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WJGC7A3PBF33LGBKSAA3VPCAAH","short_pith_number":"pith:WJGC7A3P","canonical_record":{"source":{"id":"2407.12813","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T21:41:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"575b86b6dc1f9bf02ec1d23faceb2dfceb3b2a085cc18d0c72276d6d13ec506c","abstract_canon_sha256":"581d4179d8806e86ec0ebc3a213903c32ebce5039e32900607ab8eb433a982d6"},"schema_version":"1.0"},"canonical_sha256":"b24c2f836f0977b5982a9001babc4001ccdb86107b004cf22a5b7cc7baaa7489","source":{"kind":"arxiv","id":"2407.12813","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12813","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12813v2","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12813","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_12","alias_value":"WJGC7A3PBF33","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_16","alias_value":"WJGC7A3PBF33LGBK","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_8","alias_value":"WJGC7A3P","created_at":"2026-07-05T08:46:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WJGC7A3PBF33LGBKSAA3VPCAAH","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12813","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T21:41:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"575b86b6dc1f9bf02ec1d23faceb2dfceb3b2a085cc18d0c72276d6d13ec506c","abstract_canon_sha256":"581d4179d8806e86ec0ebc3a213903c32ebce5039e32900607ab8eb433a982d6"},"schema_version":"1.0"},"canonical_sha256":"b24c2f836f0977b5982a9001babc4001ccdb86107b004cf22a5b7cc7baaa7489","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:28.029436Z","signature_b64":"88mVqrYa/6pw0xnjh+YqDhB7mYZPKtDpsByWoomrf5l0N44NNO7fcxarIO8IhJBOpwub6o99l9V+PPJp38nzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b24c2f836f0977b5982a9001babc4001ccdb86107b004cf22a5b7cc7baaa7489","last_reissued_at":"2026-07-05T08:46:28.029022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:28.029022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12813","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":"2026-07-05T08:46:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXqW9+XI26q9GIF46Pb+ECeMNJSb0KfDYMa2qTW6HVTblmJLQfLUu69ye3iXgCyrShaas8+cbY+UClyKlvaUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:28:24.115266Z"},"content_sha256":"45920fed9da9f58e3aaba63c9d890b7c84370f90e8578575cb3f8b965ccf43cc","schema_version":"1.0","event_id":"sha256:45920fed9da9f58e3aaba63c9d890b7c84370f90e8578575cb3f8b965ccf43cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WJGC7A3PBF33LGBKSAA3VPCAAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Generation Using Large Language Models for Text Classification: An Empirical Case Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Justin Wagle, Kazuhito Koishida, Rogerio Bonatti, Sara Abdali, Yinheng Li","submitted_at":"2024-06-27T21:41:43Z","abstract_excerpt":"Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is influenced by various factors, including the choice of prompt, task complexity, and the quality, quantity, and diversity of the generated data. In this work, we focus exclusively on using synthetic data for text classification tasks. Specifically, we use natural language understanding (NLU) models trained on synthetic data to assess the quality of synthetic data from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12813","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/2407.12813/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":"2026-07-05T08:46:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IINrl4Hc2D8WvUUwjWqdKMuam05E6e9+w6pHHVnaEgbyOyIyLoyd8Z7IhFKcHoqWLa2YXvpkMcS6d13e8gwNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:28:24.115624Z"},"content_sha256":"5d3bc8ae937a995924d418d9a9049d9bd12e6beab1890f06f170f842e049caa1","schema_version":"1.0","event_id":"sha256:5d3bc8ae937a995924d418d9a9049d9bd12e6beab1890f06f170f842e049caa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/bundle.json","state_url":"https://pith.science/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/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":"2026-07-31T13:28:24Z","links":{"resolver":"https://pith.science/pith/WJGC7A3PBF33LGBKSAA3VPCAAH","bundle":"https://pith.science/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/bundle.json","state":"https://pith.science/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WJGC7A3PBF33LGBKSAA3VPCAAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WJGC7A3PBF33LGBKSAA3VPCAAH","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":"581d4179d8806e86ec0ebc3a213903c32ebce5039e32900607ab8eb433a982d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T21:41:43Z","title_canon_sha256":"575b86b6dc1f9bf02ec1d23faceb2dfceb3b2a085cc18d0c72276d6d13ec506c"},"schema_version":"1.0","source":{"id":"2407.12813","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12813","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12813v2","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12813","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_12","alias_value":"WJGC7A3PBF33","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_16","alias_value":"WJGC7A3PBF33LGBK","created_at":"2026-07-05T08:46:28Z"},{"alias_kind":"pith_short_8","alias_value":"WJGC7A3P","created_at":"2026-07-05T08:46:28Z"}],"graph_snapshots":[{"event_id":"sha256:5d3bc8ae937a995924d418d9a9049d9bd12e6beab1890f06f170f842e049caa1","target":"graph","created_at":"2026-07-05T08:46:28Z","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/2407.12813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is influenced by various factors, including the choice of prompt, task complexity, and the quality, quantity, and diversity of the generated data. In this work, we focus exclusively on using synthetic data for text classification tasks. Specifically, we use natural language understanding (NLU) models trained on synthetic data to assess the quality of synthetic data from","authors_text":"Justin Wagle, Kazuhito Koishida, Rogerio Bonatti, Sara Abdali, Yinheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T21:41:43Z","title":"Data Generation Using Large Language Models for Text Classification: An Empirical Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12813","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":"sha256:45920fed9da9f58e3aaba63c9d890b7c84370f90e8578575cb3f8b965ccf43cc","target":"record","created_at":"2026-07-05T08:46:28Z","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":"581d4179d8806e86ec0ebc3a213903c32ebce5039e32900607ab8eb433a982d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T21:41:43Z","title_canon_sha256":"575b86b6dc1f9bf02ec1d23faceb2dfceb3b2a085cc18d0c72276d6d13ec506c"},"schema_version":"1.0","source":{"id":"2407.12813","kind":"arxiv","version":2}},"canonical_sha256":"b24c2f836f0977b5982a9001babc4001ccdb86107b004cf22a5b7cc7baaa7489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b24c2f836f0977b5982a9001babc4001ccdb86107b004cf22a5b7cc7baaa7489","first_computed_at":"2026-07-05T08:46:28.029022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:28.029022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88mVqrYa/6pw0xnjh+YqDhB7mYZPKtDpsByWoomrf5l0N44NNO7fcxarIO8IhJBOpwub6o99l9V+PPJp38nzCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:28.029436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12813","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45920fed9da9f58e3aaba63c9d890b7c84370f90e8578575cb3f8b965ccf43cc","sha256:5d3bc8ae937a995924d418d9a9049d9bd12e6beab1890f06f170f842e049caa1"],"state_sha256":"3e1fee5628ae2a6ce41d8f2c7d4baa64019d7467d81a7b41e3254302d26f56af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDBb4oWSNk78wqYBYqQqq4C/CAn0r/xd3uRu3iHkznNmidPVmw5LAePX3qr2E6zYZlYCcp6C08kiiVYqOP9wDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:28:24.120157Z","bundle_sha256":"f6563fa1f95a3d05455f2b37f84bd57a611e19c9b469d1497a0e15dc74095eb0"}}