{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5RWAWQ36A7U2LY43UZUSIWRXTY","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":"22dd7b53dc697f244cf8e298ee09a10978570bd8cfe6b31ee7c61e65bfb4258a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-16T14:03:30Z","title_canon_sha256":"564ba79e0ab0159847e66b2d511d23b33711b668017d0be3ac47f8ec6a0fa813"},"schema_version":"1.0","source":{"id":"2505.11270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11270","created_at":"2026-07-05T11:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11270v1","created_at":"2026-07-05T11:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11270","created_at":"2026-07-05T11:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"5RWAWQ36A7U2","created_at":"2026-07-05T11:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"5RWAWQ36A7U2LY43","created_at":"2026-07-05T11:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"5RWAWQ36","created_at":"2026-07-05T11:04:13Z"}],"graph_snapshots":[{"event_id":"sha256:e77e91fcde7bf20a764438a0c2225cb823686eba3abdbdebce9456d802e54000","target":"graph","created_at":"2026-07-05T11:04:13Z","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/2505.11270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models (LLMs) have demonstrated promising capabilities, they still remain inadequate for multi-modal data analytics in terms of accuracy, efficiency, and freshness. First, current natural language (NL) or SQL-like query languages may struggle to precisely and comprehensively capture users' analytical intent. Second, relying on a single unified LLM to process diver","authors_text":"Chao Zhang, Ju Fan, Quehuan Liu, Shaolei Zhang, Sibei Chen, Tong Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-16T14:03:30Z","title":"TAIJI: MCP-based Multi-Modal Data Analytics on Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11270","kind":"arxiv","version":1},"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":"sha256:93ec7413048d90b7d646a174f214487bebda30f1f40c2ec12ecfb1ea010b7889","target":"record","created_at":"2026-07-05T11:04:13Z","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":"22dd7b53dc697f244cf8e298ee09a10978570bd8cfe6b31ee7c61e65bfb4258a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-16T14:03:30Z","title_canon_sha256":"564ba79e0ab0159847e66b2d511d23b33711b668017d0be3ac47f8ec6a0fa813"},"schema_version":"1.0","source":{"id":"2505.11270","kind":"arxiv","version":1}},"canonical_sha256":"ec6c0b437e07e9a5e39ba669245a379e3febb473e0e983b9d0a184fe125340ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec6c0b437e07e9a5e39ba669245a379e3febb473e0e983b9d0a184fe125340ac","first_computed_at":"2026-07-05T11:04:13.670652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:13.670652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w1TQ0HLkBtlRFORXpx+/p7PTrQQHFyXcz+Zpze9ZWAEUgT3qvkt7FD8LVWpMhHg8thpSua2aAj7AOAmRiHziCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:13.671168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93ec7413048d90b7d646a174f214487bebda30f1f40c2ec12ecfb1ea010b7889","sha256:e77e91fcde7bf20a764438a0c2225cb823686eba3abdbdebce9456d802e54000"],"state_sha256":"3e117533a84bb7e3771ccbfee574b30457a5dee39091f6e33a8ce116c59f3a8b"}