{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZZGOO2N66WK3GEILFQGK5T6HZS","short_pith_number":"pith:ZZGOO2N6","canonical_record":{"source":{"id":"2310.07849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T19:51:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a164d6f6cb55ba995af2ecac03e237284f6d7271a9abde152633ead38ec0843","abstract_canon_sha256":"c03c191566f303b695aa27ed3d05dbc551f78881d6894cb6448a4074a9d28c19"},"schema_version":"1.0"},"canonical_sha256":"ce4ce769bef595b3110b2c0caecfc7cc9f89096d21b5b5e52e90306016ac0f78","source":{"kind":"arxiv","id":"2310.07849","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07849","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07849v2","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07849","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZZGOO2N66WK3","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZZGOO2N66WK3GEIL","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZZGOO2N6","created_at":"2026-07-05T07:00:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZZGOO2N66WK3GEILFQGK5T6HZS","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T19:51:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a164d6f6cb55ba995af2ecac03e237284f6d7271a9abde152633ead38ec0843","abstract_canon_sha256":"c03c191566f303b695aa27ed3d05dbc551f78881d6894cb6448a4074a9d28c19"},"schema_version":"1.0"},"canonical_sha256":"ce4ce769bef595b3110b2c0caecfc7cc9f89096d21b5b5e52e90306016ac0f78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:30.215594Z","signature_b64":"lAmdnfnaGTBbcc7EyI5gAwju/Jf42H6YkuCIS0tW4S0GjcDHWCJWOUxZeAqxGwNgtCwlvZt5Nv4+RvNjp2KECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4ce769bef595b3110b2c0caecfc7cc9f89096d21b5b5e52e90306016ac0f78","last_reissued_at":"2026-07-05T07:00:30.215147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:30.215147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07849","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":"2026-07-05T07:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"loay4MkFJPRRFB7A5puxVzauJXeYvXhj0M8UsFKIx/MygyY+9nuSiy5ANk3m2C0Y7ch1LETdgpZI3bGMqb3pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:37:43.297791Z"},"content_sha256":"a3c0f9f26c8c569c4615e90192f6ee9e12a70075b0940e2c223f1547cd4f21a9","schema_version":"1.0","event_id":"sha256:a3c0f9f26c8c569c4615e90192f6ee9e12a70075b0940e2c223f1547cd4f21a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZZGOO2N66WK3GEILFQGK5T6HZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hangxiao Zhu, Ming Yin, Zhuoran Lu, Zhuoyan Li","submitted_at":"2023-10-11T19:51:13Z","abstract_excerpt":"The collection and curation of high-quality training data is crucial for developing text classification models with superior performance, but it is often associated with significant costs and time investment. Researchers have recently explored using large language models (LLMs) to generate synthetic datasets as an alternative approach. However, the effectiveness of the LLM-generated synthetic data in supporting model training is inconsistent across different classification tasks. To better understand factors that moderate the effectiveness of the LLM-generated synthetic data, in this study, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07849","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/2310.07849/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":"2026-07-05T07:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Foj3+OJS4o6LWX/EYAnbZdqMihSKBjjr6W+7EtxleqU3bJXAaIVkducYAgBAM/yzU8gJkR+8iQ9XnE8/HFIiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:37:43.298667Z"},"content_sha256":"6ed4d9df8d3f5a579bafc2c4ef1da7d8f245310875a883b59796c682522fbd69","schema_version":"1.0","event_id":"sha256:6ed4d9df8d3f5a579bafc2c4ef1da7d8f245310875a883b59796c682522fbd69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/bundle.json","state_url":"https://pith.science/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/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":"2026-08-10T14:37:43Z","links":{"resolver":"https://pith.science/pith/ZZGOO2N66WK3GEILFQGK5T6HZS","bundle":"https://pith.science/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/bundle.json","state":"https://pith.science/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZGOO2N66WK3GEILFQGK5T6HZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZZGOO2N66WK3GEILFQGK5T6HZS","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":"c03c191566f303b695aa27ed3d05dbc551f78881d6894cb6448a4074a9d28c19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T19:51:13Z","title_canon_sha256":"6a164d6f6cb55ba995af2ecac03e237284f6d7271a9abde152633ead38ec0843"},"schema_version":"1.0","source":{"id":"2310.07849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07849","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07849v2","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07849","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZZGOO2N66WK3","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZZGOO2N66WK3GEIL","created_at":"2026-07-05T07:00:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZZGOO2N6","created_at":"2026-07-05T07:00:30Z"}],"graph_snapshots":[{"event_id":"sha256:6ed4d9df8d3f5a579bafc2c4ef1da7d8f245310875a883b59796c682522fbd69","target":"graph","created_at":"2026-07-05T07:00:30Z","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/2310.07849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The collection and curation of high-quality training data is crucial for developing text classification models with superior performance, but it is often associated with significant costs and time investment. Researchers have recently explored using large language models (LLMs) to generate synthetic datasets as an alternative approach. However, the effectiveness of the LLM-generated synthetic data in supporting model training is inconsistent across different classification tasks. To better understand factors that moderate the effectiveness of the LLM-generated synthetic data, in this study, we","authors_text":"Hangxiao Zhu, Ming Yin, Zhuoran Lu, Zhuoyan Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T19:51:13Z","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07849","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:a3c0f9f26c8c569c4615e90192f6ee9e12a70075b0940e2c223f1547cd4f21a9","target":"record","created_at":"2026-07-05T07:00:30Z","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":"c03c191566f303b695aa27ed3d05dbc551f78881d6894cb6448a4074a9d28c19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T19:51:13Z","title_canon_sha256":"6a164d6f6cb55ba995af2ecac03e237284f6d7271a9abde152633ead38ec0843"},"schema_version":"1.0","source":{"id":"2310.07849","kind":"arxiv","version":2}},"canonical_sha256":"ce4ce769bef595b3110b2c0caecfc7cc9f89096d21b5b5e52e90306016ac0f78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce4ce769bef595b3110b2c0caecfc7cc9f89096d21b5b5e52e90306016ac0f78","first_computed_at":"2026-07-05T07:00:30.215147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:30.215147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAmdnfnaGTBbcc7EyI5gAwju/Jf42H6YkuCIS0tW4S0GjcDHWCJWOUxZeAqxGwNgtCwlvZt5Nv4+RvNjp2KECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:30.215594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3c0f9f26c8c569c4615e90192f6ee9e12a70075b0940e2c223f1547cd4f21a9","sha256:6ed4d9df8d3f5a579bafc2c4ef1da7d8f245310875a883b59796c682522fbd69"],"state_sha256":"d066a5a7751c2848e156cf825d92471722a9dbc3eb12d6da01174ec8b6745cc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1DAJ+HIcM5jbbZcJ0Z20TLONU5ApAJcWkVktjb1E1zsvUktoOhHbWUwNcg0QXcayJ5ziPDQBQVdYfLQqBaQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:37:43.303522Z","bundle_sha256":"714b0fe0783cb543d83801fe5a79da84bf5e1332256d162db715c803e3a62b38"}}