{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SWMEWM5DBNHMATIR3XEMIC6SIF","short_pith_number":"pith:SWMEWM5D","schema_version":"1.0","canonical_sha256":"95984b33a30b4ec04d11ddc8c40bd2416c9afff8761ea712fff8c4d90f7ac147","source":{"kind":"arxiv","id":"2507.01599","version":1},"attestation_state":"computed","paper":{"title":"Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Jiachi Wang, Jiayi Wang, Xinyang Zhao, Zhaoyan Sun","submitted_at":"2025-07-02T11:04:49Z","abstract_excerpt":"Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For instance, while there are numerous data science tools available, developing a pipeline planning system to coordinate these tools remains challenging. This difficulty arises because existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning. Fortunately, we have witnessed the success of large language models (LLMs) in e"},"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":"2507.01599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T11:04:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"24eeda6a7ffe9704f20363e5391f73cc14662eb2771411f8be4da71da9d22600","abstract_canon_sha256":"dcb3488daa8d3b6ed6e0872c873c01c64210dc6d86118cb8a6ff84bbd388c590"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:51.650757Z","signature_b64":"JOnzqFEtFoQrpYz1B+KxSqXM8niVSuVkb+Dn9Jc26lv5cblUeBmqsx2uieEUKIqFh+Y0soHhx0STVwIeUljHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95984b33a30b4ec04d11ddc8c40bd2416c9afff8761ea712fff8c4d90f7ac147","last_reissued_at":"2026-07-05T11:30:51.650337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:51.650337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Jiachi Wang, Jiayi Wang, Xinyang Zhao, Zhaoyan Sun","submitted_at":"2025-07-02T11:04:49Z","abstract_excerpt":"Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For instance, while there are numerous data science tools available, developing a pipeline planning system to coordinate these tools remains challenging. This difficulty arises because existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning. Fortunately, we have witnessed the success of large language models (LLMs) in e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01599","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/2507.01599/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":"2507.01599","created_at":"2026-07-05T11:30:51.650397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01599v1","created_at":"2026-07-05T11:30:51.650397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01599","created_at":"2026-07-05T11:30:51.650397+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWMEWM5DBNHM","created_at":"2026-07-05T11:30:51.650397+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWMEWM5DBNHMATIR","created_at":"2026-07-05T11:30:51.650397+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWMEWM5D","created_at":"2026-07-05T11:30:51.650397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01647","citing_title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF","json":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF.json","graph_json":"https://pith.science/api/pith-number/SWMEWM5DBNHMATIR3XEMIC6SIF/graph.json","events_json":"https://pith.science/api/pith-number/SWMEWM5DBNHMATIR3XEMIC6SIF/events.json","paper":"https://pith.science/paper/SWMEWM5D"},"agent_actions":{"view_html":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF","download_json":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF.json","view_paper":"https://pith.science/paper/SWMEWM5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01599&json=true","fetch_graph":"https://pith.science/api/pith-number/SWMEWM5DBNHMATIR3XEMIC6SIF/graph.json","fetch_events":"https://pith.science/api/pith-number/SWMEWM5DBNHMATIR3XEMIC6SIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF/action/storage_attestation","attest_author":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF/action/author_attestation","sign_citation":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF/action/citation_signature","submit_replication":"https://pith.science/pith/SWMEWM5DBNHMATIR3XEMIC6SIF/action/replication_record"}},"created_at":"2026-07-05T11:30:51.650397+00:00","updated_at":"2026-07-05T11:30:51.650397+00:00"}