{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NA2DAEULCGSZ2WNGBFO7D7T76H","short_pith_number":"pith:NA2DAEUL","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"},"canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","source":{"kind":"arxiv","id":"2606.10460","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NA2DAEULCGSZ2WNGBFO7D7T76H","target":"record","payload":{"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"},"canonical_sha256":"683430128b11a59d59a6095df1fe7ff1dcbe05d85acfad455644914776b34a41","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"},"source_kind":"arxiv","source_id":"2606.10460","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8A3Doz5MZKskzVisJ++41N32MCrWq1AyHYkht06zJVFtSZmHw8g4fRK0sGlznbpL+Z10HqZcHm8McwaGn41CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T19:23:01.191386Z"},"content_sha256":"beba4950a196d01be99ffce6c66c30556f03945d9d9958563871bacaabbd5993","schema_version":"1.0","event_id":"sha256:beba4950a196d01be99ffce6c66c30556f03945d9d9958563871bacaabbd5993"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NA2DAEULCGSZ2WNGBFO7D7T76H","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XOnddzINveWpMg3mpPAAT+5xrEu2tfuXiyVE5TipVQLqDm4LW3WNYeLQ6vAlJ0yt6OeZ3eQAdLL96ALnFB09DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T19:23:01.191755Z"},"content_sha256":"944bde0e4db46ce4b90668701c4fe1cf93cc21221a1a049e01b7b5abc029b3d0","schema_version":"1.0","event_id":"sha256:944bde0e4db46ce4b90668701c4fe1cf93cc21221a1a049e01b7b5abc029b3d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/bundle.json","state_url":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-22T19:23:01Z","links":{"resolver":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H","bundle":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/bundle.json","state":"https://pith.science/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NA2DAEULCGSZ2WNGBFO7D7T76H/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bz1c394vcm/jQQGpGEk6RAhz7pSXz4dLIKZ/4S/rP/kQrUNbyjHQAcFXoS73B+Jde6+Etoidu/UEOKTXz7swDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T19:23:01.193741Z","bundle_sha256":"4eb6691818f8b3974d8bb2c4b04ad128910632e18347ad31b0b8f93449edcbf7"}}