{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MI6LS767IVFLZYFSSNB3YSE4UI","short_pith_number":"pith:MI6LS767","schema_version":"1.0","canonical_sha256":"623cb97fdf454abce0b29343bc489ca202402c93578529a9f96bd8bd97654cb0","source":{"kind":"arxiv","id":"2608.03451","version":1},"attestation_state":"computed","paper":{"title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyan Li, Guoliang Li, Jiayi Zhang, Nan Tang, Tianqi Luo, Xiaotian Lin, Xinyu Liu, Yizhang Zhu, Yuan Li, Yupeng Xie, Yuyu Luo, Zhangyang Peng, Zhengxuan Zhang, Zhuowen Liang","submitted_at":"2026-08-04T10:48:11Z","abstract_excerpt":"Data agents enable natural-language analytics over organizational workspaces, where relevant evidence may be scattered across databases, structured files, long documents, and multimedia. Existing benchmarks largely isolate structured querying, retrieval, or open-ended analysis, leaving heterogeneous evidence discovery, complete tabular outputs, and deterministic evaluation insufficiently unified. We introduce DataSpace, a benchmark in which data agents produce verifiable tabular results from task-local heterogeneous workspaces. It contains 410 cross-language tasks and 7,439 artifacts totaling "},"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":"2608.03451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"9d141919913680b69b734d47fc34096f9d0d7a4def24b7e91bdea00881e90349","abstract_canon_sha256":"da958422c833b477a3c1fa54747ad27bb46cea5c9e672e68361ffb3f875c0107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:52.621474Z","signature_b64":"0Bd5DBk2jrG9wpJKHHJWyns1bWwPDAvGy3Q78W9L4Talr8eRJq7yo9JLwCZlZHMdVb8x+ANp71wXuH/Uc14/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623cb97fdf454abce0b29343bc489ca202402c93578529a9f96bd8bd97654cb0","last_reissued_at":"2026-08-05T01:35:52.620085Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:52.620085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyan Li, Guoliang Li, Jiayi Zhang, Nan Tang, Tianqi Luo, Xiaotian Lin, Xinyu Liu, Yizhang Zhu, Yuan Li, Yupeng Xie, Yuyu Luo, Zhangyang Peng, Zhengxuan Zhang, Zhuowen Liang","submitted_at":"2026-08-04T10:48:11Z","abstract_excerpt":"Data agents enable natural-language analytics over organizational workspaces, where relevant evidence may be scattered across databases, structured files, long documents, and multimedia. Existing benchmarks largely isolate structured querying, retrieval, or open-ended analysis, leaving heterogeneous evidence discovery, complete tabular outputs, and deterministic evaluation insufficiently unified. We introduce DataSpace, a benchmark in which data agents produce verifiable tabular results from task-local heterogeneous workspaces. It contains 410 cross-language tasks and 7,439 artifacts totaling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03451","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/2608.03451/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":"2608.03451","created_at":"2026-08-05T01:35:52.620503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03451v1","created_at":"2026-08-05T01:35:52.620503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03451","created_at":"2026-08-05T01:35:52.620503+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI6LS767IVFL","created_at":"2026-08-05T01:35:52.620503+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI6LS767IVFLZYFS","created_at":"2026-08-05T01:35:52.620503+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI6LS767","created_at":"2026-08-05T01:35:52.620503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08459","citing_title":"Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI","json":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI.json","graph_json":"https://pith.science/api/pith-number/MI6LS767IVFLZYFSSNB3YSE4UI/graph.json","events_json":"https://pith.science/api/pith-number/MI6LS767IVFLZYFSSNB3YSE4UI/events.json","paper":"https://pith.science/paper/MI6LS767"},"agent_actions":{"view_html":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI","download_json":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI.json","view_paper":"https://pith.science/paper/MI6LS767","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03451&json=true","fetch_graph":"https://pith.science/api/pith-number/MI6LS767IVFLZYFSSNB3YSE4UI/graph.json","fetch_events":"https://pith.science/api/pith-number/MI6LS767IVFLZYFSSNB3YSE4UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI/action/storage_attestation","attest_author":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI/action/author_attestation","sign_citation":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI/action/citation_signature","submit_replication":"https://pith.science/pith/MI6LS767IVFLZYFSSNB3YSE4UI/action/replication_record"}},"created_at":"2026-08-05T01:35:52.620503+00:00","updated_at":"2026-08-05T01:35:52.620503+00:00"}