{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NA2DAEULCGSZ2WNGBFO7D7T76H","short_pith_number":"pith:NA2DAEUL","schema_version":"1.0","canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","source":{"kind":"arxiv","id":"2606.10460","version":1},"attestation_state":"computed","paper":{"title":"LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Austin Senna Wijaya, Daniela Pinto, Eden Wu, Eugene Wu, Grace Fan, Haonan Wang, Jiaxiang Liu, Juliana Freire, Reya Vir, Tianle Zhou, Wanting You, Yijia Chen, Yurong Liu, Yusen Zhang","submitted_at":"2026-06-09T06:15:36Z","abstract_excerpt":"Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In contrast, real-world questions are often not paired with accurate evidence documents. The useful evidence resides in massive data lakes, making search a prerequisite for answering. However, there is a lack of comprehensive benchmarks that require both searching and reasoning over large data lakes. To this end, we introduce LakeQA, a comprehensive benchmark for search-centric question answering over data lakes that jointl"},"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":"2606.10460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T06:15:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94a1071c3deef3eb87ad6c28fdf69a6f1ca4c2f050fd3c7a37d7be59dbfccc1a","abstract_canon_sha256":"323dd6a073f3145ec8d9c4de972aa9607e9c80c86f1a76969942491131a97cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:20.401343Z","signature_b64":"Zd7igehN6yGip/9gmm6PQiDWXHkKABGZv/3hVn+OjyQ9jBTkvATKKImMYi581+XMU3OFY+ntP/YtIuj8U7C4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","last_reissued_at":"2026-06-10T01:10:20.400475Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:20.400475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Austin Senna Wijaya, Daniela Pinto, Eden Wu, Eugene Wu, Grace Fan, Haonan Wang, Jiaxiang Liu, Juliana Freire, Reya Vir, Tianle Zhou, Wanting You, Yijia Chen, Yurong Liu, Yusen Zhang","submitted_at":"2026-06-09T06:15:36Z","abstract_excerpt":"Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In contrast, real-world questions are often not paired with accurate evidence documents. The useful evidence resides in massive data lakes, making search a prerequisite for answering. However, there is a lack of comprehensive benchmarks that require both searching and reasoning over large data lakes. To this end, we introduce LakeQA, a comprehensive benchmark for search-centric question answering over data lakes that jointl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10460","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/2606.10460/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":"2606.10460","created_at":"2026-06-10T01:10:20.400603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10460v1","created_at":"2026-06-10T01:10:20.400603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10460","created_at":"2026-06-10T01:10:20.400603+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA2DAEULCGSZ","created_at":"2026-06-10T01:10:20.400603+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA2DAEULCGSZ2WNG","created_at":"2026-06-10T01:10:20.400603+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA2DAEUL","created_at":"2026-06-10T01:10:20.400603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H","json":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H.json","graph_json":"https://pith.science/api/pith-number/NA2DAEULCGSZ2WNGBFO7D7T76H/graph.json","events_json":"https://pith.science/api/pith-number/NA2DAEULCGSZ2WNGBFO7D7T76H/events.json","paper":"https://pith.science/paper/NA2DAEUL"},"agent_actions":{"view_html":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H","download_json":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H.json","view_paper":"https://pith.science/paper/NA2DAEUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10460&json=true","fetch_graph":"https://pith.science/api/pith-number/NA2DAEULCGSZ2WNGBFO7D7T76H/graph.json","fetch_events":"https://pith.science/api/pith-number/NA2DAEULCGSZ2WNGBFO7D7T76H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/action/storage_attestation","attest_author":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/action/author_attestation","sign_citation":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/action/citation_signature","submit_replication":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/action/replication_record"}},"created_at":"2026-06-10T01:10:20.400603+00:00","updated_at":"2026-06-10T01:10:20.400603+00:00"}