{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTNZSBJTULUGRGPPELE63S3DKA","short_pith_number":"pith:YTNZSBJT","schema_version":"1.0","canonical_sha256":"c4db990533a2e86899ef22c9edcb6350312bdc8f9d04b798203ff0284c002e79","source":{"kind":"arxiv","id":"2509.02473","version":2},"attestation_state":"computed","paper":{"title":"FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Gao Cong, Haitao Yuan, Jinwei Zhu, Shize Zhang, Wei Dong, Ziting Wang","submitted_at":"2025-09-02T16:25:12Z","abstract_excerpt":"The growing demand for data-driven decision-making has created an urgent need for data agents that can reason over heterogeneous data (databases, documents, web content, images, videos, and audio) to answer complex analytical queries. However, evaluating such agents remains challenging: existing benchmarks often focus on isolated agent capabilities or limited data modalities, lacking comprehensive coverage of heterogeneous data and rigorous evaluation across diverse data agent architectures. To address these challenges, we present FDABench, a benchmark for evaluating data agents' reasoning abi"},"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":"2509.02473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T16:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"e03296df3ba4b0dd86c797fda65d807899e0233dfeace4d4d79021b0811298c8","abstract_canon_sha256":"f521143757d80fceec6116d7f97e18875f7a6c34b3fa965214e9f1e34463477f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:45.034582Z","signature_b64":"Teej5a9OnJu7REUM65o//+GFd2j9b4MnpKYuCcE48AtjiPDq6r7iNokI4z/nMgv2WwktYi4xO6AmuCKK5YhgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4db990533a2e86899ef22c9edcb6350312bdc8f9d04b798203ff0284c002e79","last_reissued_at":"2026-06-01T01:03:45.033483Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:45.033483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Gao Cong, Haitao Yuan, Jinwei Zhu, Shize Zhang, Wei Dong, Ziting Wang","submitted_at":"2025-09-02T16:25:12Z","abstract_excerpt":"The growing demand for data-driven decision-making has created an urgent need for data agents that can reason over heterogeneous data (databases, documents, web content, images, videos, and audio) to answer complex analytical queries. However, evaluating such agents remains challenging: existing benchmarks often focus on isolated agent capabilities or limited data modalities, lacking comprehensive coverage of heterogeneous data and rigorous evaluation across diverse data agent architectures. To address these challenges, we present FDABench, a benchmark for evaluating data agents' reasoning abi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02473","kind":"arxiv","version":2},"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/2509.02473/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":"2509.02473","created_at":"2026-06-01T01:03:45.033654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02473v2","created_at":"2026-06-01T01:03:45.033654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02473","created_at":"2026-06-01T01:03:45.033654+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTNZSBJTULUG","created_at":"2026-06-01T01:03:45.033654+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTNZSBJTULUGRGPP","created_at":"2026-06-01T01:03:45.033654+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTNZSBJT","created_at":"2026-06-01T01:03:45.033654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.00051","citing_title":"Business Utility of Large Language Models as Exploratory Data Analysis Agents","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA","json":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA.json","graph_json":"https://pith.science/api/pith-number/YTNZSBJTULUGRGPPELE63S3DKA/graph.json","events_json":"https://pith.science/api/pith-number/YTNZSBJTULUGRGPPELE63S3DKA/events.json","paper":"https://pith.science/paper/YTNZSBJT"},"agent_actions":{"view_html":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA","download_json":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA.json","view_paper":"https://pith.science/paper/YTNZSBJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02473&json=true","fetch_graph":"https://pith.science/api/pith-number/YTNZSBJTULUGRGPPELE63S3DKA/graph.json","fetch_events":"https://pith.science/api/pith-number/YTNZSBJTULUGRGPPELE63S3DKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA/action/storage_attestation","attest_author":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA/action/author_attestation","sign_citation":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA/action/citation_signature","submit_replication":"https://pith.science/pith/YTNZSBJTULUGRGPPELE63S3DKA/action/replication_record"}},"created_at":"2026-06-01T01:03:45.033654+00:00","updated_at":"2026-06-01T01:03:45.033654+00:00"}