{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2OKSZJQUTKNSRGKK6BH3OUY6G","short_pith_number":"pith:O2OKSZJQ","schema_version":"1.0","canonical_sha256":"769ca96530a4d4d944ca57827dba98f19f5a938ce269211ef36fa3101213543a","source":{"kind":"arxiv","id":"2402.13446","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models for Data Annotation and Synthesis: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alimohammad Beigi, Amrita Bhattacharjee, Bohan Jiang, Dawei Li, Huan Liu, Jundong Li, Lu Cheng, Mansooreh Karami, Song Wang, Zhen Tan","submitted_at":"2024-02-21T00:44:04Z","abstract_excerpt":"Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and costly. The emergence of advanced Large Language Models (LLMs), exemplified by GPT-4, presents an unprecedented opportunity to automate the complicated process of data annotation and synthesis. While existing surveys have extensively covered LLM architecture, training, and general applications, we uniquely focus on their specific utility for data annotation. Thi"},"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":"2402.13446","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:44:04Z","cross_cats_sorted":[],"title_canon_sha256":"a856c10eb052171a89a68a2ef69e6e8840aedd74a709aa2ecf590a1f55ca8faa","abstract_canon_sha256":"825c28dd48ee7d8f6fd26bfbb40fd6d87640aec0981bda468cd1746d50b81668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:27.496457Z","signature_b64":"VXGTe/2mLaKfjQI07U9B1aj8sglwIHy/gPJJrsSrMt0gE3mLcfprdbfIV4oYg1ZjZrgPDjuf1gzjY7EtjG7oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"769ca96530a4d4d944ca57827dba98f19f5a938ce269211ef36fa3101213543a","last_reissued_at":"2026-07-05T09:43:27.495953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:27.495953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Data Annotation and Synthesis: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alimohammad Beigi, Amrita Bhattacharjee, Bohan Jiang, Dawei Li, Huan Liu, Jundong Li, Lu Cheng, Mansooreh Karami, Song Wang, Zhen Tan","submitted_at":"2024-02-21T00:44:04Z","abstract_excerpt":"Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and costly. The emergence of advanced Large Language Models (LLMs), exemplified by GPT-4, presents an unprecedented opportunity to automate the complicated process of data annotation and synthesis. While existing surveys have extensively covered LLM architecture, training, and general applications, we uniquely focus on their specific utility for data annotation. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13446","kind":"arxiv","version":3},"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/2402.13446/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":"2402.13446","created_at":"2026-07-05T09:43:27.496015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13446v3","created_at":"2026-07-05T09:43:27.496015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13446","created_at":"2026-07-05T09:43:27.496015+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2OKSZJQUTKN","created_at":"2026-07-05T09:43:27.496015+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2OKSZJQUTKNSRGK","created_at":"2026-07-05T09:43:27.496015+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2OKSZJQ","created_at":"2026-07-05T09:43:27.496015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02953","citing_title":"Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14752","citing_title":"Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29442","citing_title":"AI in the Wild: A Large Scale Analysis of Authentic Interactions of College Students with Generative AI","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.01605","citing_title":"A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08986","citing_title":"CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08986","citing_title":"CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09548","citing_title":"Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11268","citing_title":"Context-Aware Spear Phishing: Generative AI-Enabled Attacks Against Individuals via Public Social Media Data","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06232","citing_title":"Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22597","citing_title":"Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05483","citing_title":"Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G","json":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G.json","graph_json":"https://pith.science/api/pith-number/O2OKSZJQUTKNSRGKK6BH3OUY6G/graph.json","events_json":"https://pith.science/api/pith-number/O2OKSZJQUTKNSRGKK6BH3OUY6G/events.json","paper":"https://pith.science/paper/O2OKSZJQ"},"agent_actions":{"view_html":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G","download_json":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G.json","view_paper":"https://pith.science/paper/O2OKSZJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13446&json=true","fetch_graph":"https://pith.science/api/pith-number/O2OKSZJQUTKNSRGKK6BH3OUY6G/graph.json","fetch_events":"https://pith.science/api/pith-number/O2OKSZJQUTKNSRGKK6BH3OUY6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G/action/storage_attestation","attest_author":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G/action/author_attestation","sign_citation":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G/action/citation_signature","submit_replication":"https://pith.science/pith/O2OKSZJQUTKNSRGKK6BH3OUY6G/action/replication_record"}},"created_at":"2026-07-05T09:43:27.496015+00:00","updated_at":"2026-07-05T09:43:27.496015+00:00"}