{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K6PAPKSP7BXWZ6R4FKTJBNPV4G","short_pith_number":"pith:K6PAPKSP","schema_version":"1.0","canonical_sha256":"579e07aa4ff86f6cfa3c2aa690b5f5e1b9cef6cd040390acac416b2fc096dd3c","source":{"kind":"arxiv","id":"2410.12896","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Data Synthesis and Augmentation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenkai Zhang, Jiahui Zhu, Ke Wang, Minjie Ren, Qingjie Liu, Qiqi Zhan, Shiwei Li, Xiaoyu Wu, Yunhong Wang, Zeming Liu, Zongye Zhang","submitted_at":"2024-10-16T16:12:39Z","abstract_excerpt":"The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the expansion of training datasets, leading to a looming data exhaustion crisis. This underscores the urgent need to enhance data efficiency and explore new data sources. In this context, synthetic data has emerged as a promising solution. Currently, data generation primarily consists of two major approaches: data augmentation and synthesis. This paper comprehensively "},"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":"2410.12896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T16:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"b6c2358125de7ebde6d682ee5b6432f61c06a09bcc15bc9cd45c5f493ff25aea","abstract_canon_sha256":"b747e8e7df84b446173cdf05f5a0f0afe6feca222ffb526ef846434fd2901477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:52.610802Z","signature_b64":"Y0lCHqjGUnfvikfMRwckJ6XglmQiaB6LeDY7A3Bl8dD9tbQsZO9MkJv9Ii6eoiWzScTcZkWDYndoklCLS1vTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"579e07aa4ff86f6cfa3c2aa690b5f5e1b9cef6cd040390acac416b2fc096dd3c","last_reissued_at":"2026-07-05T09:21:52.610450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:52.610450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Data Synthesis and Augmentation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenkai Zhang, Jiahui Zhu, Ke Wang, Minjie Ren, Qingjie Liu, Qiqi Zhan, Shiwei Li, Xiaoyu Wu, Yunhong Wang, Zeming Liu, Zongye Zhang","submitted_at":"2024-10-16T16:12:39Z","abstract_excerpt":"The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the expansion of training datasets, leading to a looming data exhaustion crisis. This underscores the urgent need to enhance data efficiency and explore new data sources. In this context, synthetic data has emerged as a promising solution. Currently, data generation primarily consists of two major approaches: data augmentation and synthesis. This paper comprehensively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12896","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/2410.12896/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":"2410.12896","created_at":"2026-07-05T09:21:52.610504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12896v1","created_at":"2026-07-05T09:21:52.610504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12896","created_at":"2026-07-05T09:21:52.610504+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6PAPKSP7BXW","created_at":"2026-07-05T09:21:52.610504+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6PAPKSP7BXWZ6R4","created_at":"2026-07-05T09:21:52.610504+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6PAPKSP","created_at":"2026-07-05T09:21:52.610504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19640","citing_title":"Creating Multilingual Mental Health Dialogue Datasets: Limits of Persona-Based Localization via Nationality and Language","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17270","citing_title":"Beyond Detection: A Structure-Aware Framework for Scene Text Tracking","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14380","citing_title":"Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18539","citing_title":"Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G","json":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G.json","graph_json":"https://pith.science/api/pith-number/K6PAPKSP7BXWZ6R4FKTJBNPV4G/graph.json","events_json":"https://pith.science/api/pith-number/K6PAPKSP7BXWZ6R4FKTJBNPV4G/events.json","paper":"https://pith.science/paper/K6PAPKSP"},"agent_actions":{"view_html":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G","download_json":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G.json","view_paper":"https://pith.science/paper/K6PAPKSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12896&json=true","fetch_graph":"https://pith.science/api/pith-number/K6PAPKSP7BXWZ6R4FKTJBNPV4G/graph.json","fetch_events":"https://pith.science/api/pith-number/K6PAPKSP7BXWZ6R4FKTJBNPV4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G/action/storage_attestation","attest_author":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G/action/author_attestation","sign_citation":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G/action/citation_signature","submit_replication":"https://pith.science/pith/K6PAPKSP7BXWZ6R4FKTJBNPV4G/action/replication_record"}},"created_at":"2026-07-05T09:21:52.610504+00:00","updated_at":"2026-07-05T09:21:52.610504+00:00"}