{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T6QNMILNHONJDJPWNE3KEHOU6L","short_pith_number":"pith:T6QNMILN","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"},"canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","source":{"kind":"arxiv","id":"2505.18458","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18458","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18458v3","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18458","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"T6QNMILNHONJ","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"T6QNMILNHONJDJPW","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"T6QNMILN","created_at":"2026-07-05T11:13:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T6QNMILNHONJDJPWNE3KEHOU6L","target":"record","payload":{"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"},"canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","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"},"source_kind":"arxiv","source_id":"2505.18458","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3UYnfxy4UFUzoSBZ72TL7ZRDp43vuYHFcgbLZyY9j6clC9wShDFaEsHuGKyWUXlDXWkC8cGFKP5lKSi6NQBWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:11.532752Z"},"content_sha256":"b75d1aaa289f3d7e8649166500955a83a903270db34f86218918aa6a619da919","schema_version":"1.0","event_id":"sha256:b75d1aaa289f3d7e8649166500955a83a903270db34f86218918aa6a619da919"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T6QNMILNHONJDJPWNE3KEHOU6L","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ym+CsWdEAfAdutbBTxp4aSSnV3phyl7uunrvQll40+NghmWgh/Nq9lFb+VtxUK1bbfL6QRTCSich+ctSDUxNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:11.533313Z"},"content_sha256":"4366b268894022dc86b01b4247b891851d91471b10ca7db49cf34985c74ee1f0","schema_version":"1.0","event_id":"sha256:4366b268894022dc86b01b4247b891851d91471b10ca7db49cf34985c74ee1f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/bundle.json","state_url":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6QNMILNHONJDJPWNE3KEHOU6L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T22:36:11Z","links":{"resolver":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L","bundle":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/bundle.json","state":"https://pith.science/pith/T6QNMILNHONJDJPWNE3KEHOU6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6QNMILNHONJDJPWNE3KEHOU6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T6QNMILNHONJDJPWNE3KEHOU6L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"666ab1c70f0257564f857539e640c8e949dc9caef8c1a561861b3b135e0ad17d","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-24T01:57:12Z","title_canon_sha256":"71294b9fb48c29492bd8315bb9af724e3c9f2eaaed825209a9fd865260470eee"},"schema_version":"1.0","source":{"id":"2505.18458","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18458","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18458v3","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18458","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"T6QNMILNHONJ","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"T6QNMILNHONJDJPW","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"T6QNMILN","created_at":"2026-07-05T11:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:4366b268894022dc86b01b4247b891851d91471b10ca7db49cf34985c74ee1f0","target":"graph","created_at":"2026-07-05T11:13:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.18458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-24T01:57:12Z","title":"A Survey of LLM $\\times$ DATA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18458","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b75d1aaa289f3d7e8649166500955a83a903270db34f86218918aa6a619da919","target":"record","created_at":"2026-07-05T11:13:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"666ab1c70f0257564f857539e640c8e949dc9caef8c1a561861b3b135e0ad17d","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-24T01:57:12Z","title_canon_sha256":"71294b9fb48c29492bd8315bb9af724e3c9f2eaaed825209a9fd865260470eee"},"schema_version":"1.0","source":{"id":"2505.18458","kind":"arxiv","version":3}},"canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fa0d6216d3b9a91a5f66936a21dd4f2faaf488894ca26e244e4ad8a2db87243","first_computed_at":"2026-07-05T11:13:26.611563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:26.611563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KYGnmGxvjZ3cYQGrppkyLh5lpnTwaK0TZh93+rxsbIbhPkBMMbu7YMj+2vaFHN9xTfAMfBdHg3LRFdQV9i/pAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:26.612071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18458","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b75d1aaa289f3d7e8649166500955a83a903270db34f86218918aa6a619da919","sha256:4366b268894022dc86b01b4247b891851d91471b10ca7db49cf34985c74ee1f0"],"state_sha256":"8750302f17e9433fe504c41b6dd0c93067157e581cfa84d53491a93450ee6764"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jv9S3dkeUoR+o0ELTG7HIxOQBkp5pm3g31ZbsQborSYA2Fd5eDq3C+M/Ro8VUbLL5MBxWgSoJZwuyJjkM9rsBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:36:11.538126Z","bundle_sha256":"6f96b9b5387d0e544c534e2883af0607f2d61f41aba6fc880efae9b7cdd3c087"}}