{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T6QNMILNHONJDJPWNE3KEHOU6L","short_pith_number":"pith:T6QNMILN","schema_version":"1.0","canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","source":{"kind":"arxiv","id":"2505.18458","version":3},"attestation_state":"computed","paper":{"title":"A Survey of LLM $\\times$ DATA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Binyuan Hui, Conghui He, Fan Wu, Guoliang Li, Haodong Chen, Haoyu Zhao, Jingren Zhou, Junxuan He, Jun Zhou, Shuo Wang, Wei Zhou, Xin Tong, Xuanhe Zhou, Youmin Chen, Zhaojun Sun, Zhiyuan Liu, Zirui Tang","submitted_at":"2025-05-24T01:57:12Z","abstract_excerpt":"The integration of large language model (LLM) and data management (DATA) is rapidly redefining both domains. In this survey, we comprehensively review the bidirectional relationships. On the one hand, DATA4LLM, spanning large-scale data processing, storage, and serving, feeds LLMs with high quality, diversity, and timeliness of data required for stages like pre-training, post-training, retrieval-augmented generation, and agentic workflows: (i) Data processing for LLMs includes scalable acquisition, deduplication, filtering, selection, domain mixing, and synthetic augmentation; (ii) Data Storag"},"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":"2505.18458","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-24T01:57:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"71294b9fb48c29492bd8315bb9af724e3c9f2eaaed825209a9fd865260470eee","abstract_canon_sha256":"666ab1c70f0257564f857539e640c8e949dc9caef8c1a561861b3b135e0ad17d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:26.612071Z","signature_b64":"KYGnmGxvjZ3cYQGrppkyLh5lpnTwaK0TZh93+rxsbIbhPkBMMbu7YMj+2vaFHN9xTfAMfBdHg3LRFdQV9i/pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","last_reissued_at":"2026-07-05T11:13:26.611563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:26.611563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of LLM $\\times$ DATA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Binyuan Hui, Conghui He, Fan Wu, Guoliang Li, Haodong Chen, Haoyu Zhao, Jingren Zhou, Junxuan He, Jun Zhou, Shuo Wang, Wei Zhou, Xin Tong, Xuanhe Zhou, Youmin Chen, Zhaojun Sun, Zhiyuan Liu, Zirui Tang","submitted_at":"2025-05-24T01:57:12Z","abstract_excerpt":"The integration of large language model (LLM) and data management (DATA) is rapidly redefining both domains. In this survey, we comprehensively review the bidirectional relationships. On the one hand, DATA4LLM, spanning large-scale data processing, storage, and serving, feeds LLMs with high quality, diversity, and timeliness of data required for stages like pre-training, post-training, retrieval-augmented generation, and agentic workflows: (i) Data processing for LLMs includes scalable acquisition, deduplication, filtering, selection, domain mixing, and synthetic augmentation; (ii) Data Storag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18458","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/2505.18458/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":"2505.18458","created_at":"2026-07-05T11:13:26.611626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18458v3","created_at":"2026-07-05T11:13:26.611626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18458","created_at":"2026-07-05T11:13:26.611626+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6QNMILNHONJ","created_at":"2026-07-05T11:13:26.611626+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6QNMILNHONJDJPW","created_at":"2026-07-05T11:13:26.611626+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6QNMILN","created_at":"2026-07-05T11:13:26.611626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30371","citing_title":"MaDI-Bench: An End-to-End Data Integration Benchmark","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06231","citing_title":"Automating Database-Native Function Code Synthesis with LLMs","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08687","citing_title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10480","citing_title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L","json":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L.json","graph_json":"https://pith.science/api/pith-number/T6QNMILNHONJDJPWNE3KEHOU6L/graph.json","events_json":"https://pith.science/api/pith-number/T6QNMILNHONJDJPWNE3KEHOU6L/events.json","paper":"https://pith.science/paper/T6QNMILN"},"agent_actions":{"view_html":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L","download_json":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L.json","view_paper":"https://pith.science/paper/T6QNMILN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18458&json=true","fetch_graph":"https://pith.science/api/pith-number/T6QNMILNHONJDJPWNE3KEHOU6L/graph.json","fetch_events":"https://pith.science/api/pith-number/T6QNMILNHONJDJPWNE3KEHOU6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/action/storage_attestation","attest_author":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/action/author_attestation","sign_citation":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/action/citation_signature","submit_replication":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/action/replication_record"}},"created_at":"2026-07-05T11:13:26.611626+00:00","updated_at":"2026-07-05T11:13:26.611626+00:00"}