{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W5IJQHMB3VFHQMXDB6X4Y4HMQH","short_pith_number":"pith:W5IJQHMB","schema_version":"1.0","canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","source":{"kind":"arxiv","id":"2406.15126","version":1},"attestation_state":"computed","paper":{"title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gang Chen, Haobo Wang, Junbo Zhao, Lin Long, Rui Wang, Ruixuan Xiao, Xiao Ding","submitted_at":"2024-06-14T07:47:09Z","abstract_excerpt":"Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of real-world data with synthetic data generation. However, current investigations into this field lack a unified framework and mostly stay on the surface. Therefore, this paper provides an organization of relevant studies based on a generic workflow of synthetic data generation. By doing so, we highlight the gaps within existing research and outline prospective av"},"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":"2406.15126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T07:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"3bca951607f960bc01f36a578530a7a148a7e140406fd3dcfb35e075134419d3","abstract_canon_sha256":"5e681137d605bae5dffde63508ef8643c40676f3d50cbf205aeef5b9a283d8da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:14.417996Z","signature_b64":"BHXFmyXayL1Dc+QAnfT4JxeAyEezbnzT2KBFkp+vk2xcMA61fwR02sRUjHhzeJmvbwizmg1ufPpSmHuR0XL6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b750981d81dd4a7832e30fafcc70ec81c4976d936651d90002be5fd559212e3f","last_reissued_at":"2026-07-05T08:35:14.417587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:14.417587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gang Chen, Haobo Wang, Junbo Zhao, Lin Long, Rui Wang, Ruixuan Xiao, Xiao Ding","submitted_at":"2024-06-14T07:47:09Z","abstract_excerpt":"Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of real-world data with synthetic data generation. However, current investigations into this field lack a unified framework and mostly stay on the surface. Therefore, this paper provides an organization of relevant studies based on a generic workflow of synthetic data generation. By doing so, we highlight the gaps within existing research and outline prospective av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15126","kind":"arxiv","version":1},"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/2406.15126/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":"2406.15126","created_at":"2026-07-05T08:35:14.417645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15126v1","created_at":"2026-07-05T08:35:14.417645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15126","created_at":"2026-07-05T08:35:14.417645+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5IJQHMB3VFH","created_at":"2026-07-05T08:35:14.417645+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5IJQHMB3VFHQMXD","created_at":"2026-07-05T08:35:14.417645+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5IJQHMB","created_at":"2026-07-05T08:35:14.417645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12443","citing_title":"Occupational Prompting Reveals Cultural Bias in Large Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30529","citing_title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30637","citing_title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13217","citing_title":"Sustainability via LLM Right-sizing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20605","citing_title":"TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12296","citing_title":"Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directions","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2407.21772","citing_title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24544","citing_title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH","json":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH.json","graph_json":"https://pith.science/api/pith-number/W5IJQHMB3VFHQMXDB6X4Y4HMQH/graph.json","events_json":"https://pith.science/api/pith-number/W5IJQHMB3VFHQMXDB6X4Y4HMQH/events.json","paper":"https://pith.science/paper/W5IJQHMB"},"agent_actions":{"view_html":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH","download_json":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH.json","view_paper":"https://pith.science/paper/W5IJQHMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15126&json=true","fetch_graph":"https://pith.science/api/pith-number/W5IJQHMB3VFHQMXDB6X4Y4HMQH/graph.json","fetch_events":"https://pith.science/api/pith-number/W5IJQHMB3VFHQMXDB6X4Y4HMQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/action/storage_attestation","attest_author":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/action/author_attestation","sign_citation":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/action/citation_signature","submit_replication":"https://pith.science/pith/W5IJQHMB3VFHQMXDB6X4Y4HMQH/action/replication_record"}},"created_at":"2026-07-05T08:35:14.417645+00:00","updated_at":"2026-07-05T08:35:14.417645+00:00"}