{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NVJCIWALMUZ6WTT46TJLWMDYWN","short_pith_number":"pith:NVJCIWAL","schema_version":"1.0","canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","source":{"kind":"arxiv","id":"2402.18041","version":1},"attestation_state":"computed","paper":{"title":"Datasets for Large Language Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongyu Liu, Jiahuan Cao, Kai Ding, Lianwen Jin, Yang Liu","submitted_at":"2024-02-28T04:35:51Z","abstract_excerpt":"This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspect"},"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":"2402.18041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e377a701893a4aa2169f6ca4e9b00d72c047fdceef1cda42cffc941943d5a7e7","abstract_canon_sha256":"04fc2ebc0bdadcfa83dbff4d781bec07ed7b6263e5c1ee318dd4c18f68cd3769"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:11.320682Z","signature_b64":"FCyb2IuBbDpPGnIaNjPSBhR+ye+quR5Hhwg+rvjbkwwKbf6rSSJ84FwnwARtIJFa+n30/8ZY7fdJ/mRNtQaeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","last_reissued_at":"2026-07-05T07:50:11.320216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:11.320216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Datasets for Large Language Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongyu Liu, Jiahuan Cao, Kai Ding, Lianwen Jin, Yang Liu","submitted_at":"2024-02-28T04:35:51Z","abstract_excerpt":"This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18041","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/2402.18041/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":"2402.18041","created_at":"2026-07-05T07:50:11.320273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18041v1","created_at":"2026-07-05T07:50:11.320273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18041","created_at":"2026-07-05T07:50:11.320273+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVJCIWALMUZ6","created_at":"2026-07-05T07:50:11.320273+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVJCIWALMUZ6WTT4","created_at":"2026-07-05T07:50:11.320273+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVJCIWAL","created_at":"2026-07-05T07:50:11.320273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02970","citing_title":"Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models","ref_index":6,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06423","citing_title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","ref_index":27,"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":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19438","citing_title":"Malicious ML Model Detection by Learning Dynamic Behaviors","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN","json":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN.json","graph_json":"https://pith.science/api/pith-number/NVJCIWALMUZ6WTT46TJLWMDYWN/graph.json","events_json":"https://pith.science/api/pith-number/NVJCIWALMUZ6WTT46TJLWMDYWN/events.json","paper":"https://pith.science/paper/NVJCIWAL"},"agent_actions":{"view_html":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN","download_json":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN.json","view_paper":"https://pith.science/paper/NVJCIWAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18041&json=true","fetch_graph":"https://pith.science/api/pith-number/NVJCIWALMUZ6WTT46TJLWMDYWN/graph.json","fetch_events":"https://pith.science/api/pith-number/NVJCIWALMUZ6WTT46TJLWMDYWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/action/storage_attestation","attest_author":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/action/author_attestation","sign_citation":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/action/citation_signature","submit_replication":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/action/replication_record"}},"created_at":"2026-07-05T07:50:11.320273+00:00","updated_at":"2026-07-05T07:50:11.320273+00:00"}