{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NA2DAEULCGSZ2WNGBFO7D7T76H","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":"323dd6a073f3145ec8d9c4de972aa9607e9c80c86f1a76969942491131a97cad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T06:15:36Z","title_canon_sha256":"94a1071c3deef3eb87ad6c28fdf69a6f1ca4c2f050fd3c7a37d7be59dbfccc1a"},"schema_version":"1.0","source":{"id":"2606.10460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10460","created_at":"2026-06-10T01:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10460v1","created_at":"2026-06-10T01:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10460","created_at":"2026-06-10T01:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"NA2DAEULCGSZ","created_at":"2026-06-10T01:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"NA2DAEULCGSZ2WNG","created_at":"2026-06-10T01:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"NA2DAEUL","created_at":"2026-06-10T01:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:944bde0e4db46ce4b90668701c4fe1cf93cc21221a1a049e01b7b5abc029b3d0","target":"graph","created_at":"2026-06-10T01:10:20Z","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/2606.10460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T06:15:36Z","title":"LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10460","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:beba4950a196d01be99ffce6c66c30556f03945d9d9958563871bacaabbd5993","target":"record","created_at":"2026-06-10T01:10:20Z","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":"323dd6a073f3145ec8d9c4de972aa9607e9c80c86f1a76969942491131a97cad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T06:15:36Z","title_canon_sha256":"94a1071c3deef3eb87ad6c28fdf69a6f1ca4c2f050fd3c7a37d7be59dbfccc1a"},"schema_version":"1.0","source":{"id":"2606.10460","kind":"arxiv","version":1}},"canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","first_computed_at":"2026-06-10T01:10:20.400475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:20.400475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zd7igehN6yGip/9gmm6PQiDWXHkKABGZv/3hVn+OjyQ9jBTkvATKKImMYi581+XMU3OFY+ntP/YtIuj8U7C4Cg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:20.401343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beba4950a196d01be99ffce6c66c30556f03945d9d9958563871bacaabbd5993","sha256:944bde0e4db46ce4b90668701c4fe1cf93cc21221a1a049e01b7b5abc029b3d0"],"state_sha256":"492266bd9b5dbef63f15510826a5b55fbb66f915c847297ae381b7cc75c125be"}