{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LGI6SG4QDQVWA63QSF2BPFQ5TY","short_pith_number":"pith:LGI6SG4Q","schema_version":"1.0","canonical_sha256":"5991e91b901c2b607b70917417961d9e2bac559e809f992a5ffd456c284f7d93","source":{"kind":"arxiv","id":"2606.04646","version":1},"attestation_state":"computed","paper":{"title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chang Liu, Ke-Wei Huang, Mengao Zhang, Tianhui Tan, Xiang Yang","submitted_at":"2026-06-03T09:14:43Z","abstract_excerpt":"Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimized primarily for semantic relevance, but retrieving plausible passages does not guarantee correct query execution. We introduce QO-Bench, a diagnostic benchmark for query-operator question answering over typed event tuples. The benchmark covers 22,984 news articles and 614 corporate events across 18 query templates, evaluated on 785 questions. Each gold answer is deterministic"},"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":"2606.04646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T09:14:43Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"85ee90f21826535f803a2cdde29fa0db87898724260fb49fcfed055fef008504","abstract_canon_sha256":"3f1101c87b0fe5014b46a9c63f1355767ee4df729a5f962d661d5698b4c3a173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:22.932166Z","signature_b64":"wJNEs4CiAk7iG12p2EHN6/v4PnLl4xmd1OgjUEz+MJVpPAkGaDG7ptKrMEyGcFKjR9cG0rMzYgYOWC/+VJZPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5991e91b901c2b607b70917417961d9e2bac559e809f992a5ffd456c284f7d93","last_reissued_at":"2026-06-04T01:09:22.931519Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:22.931519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chang Liu, Ke-Wei Huang, Mengao Zhang, Tianhui Tan, Xiang Yang","submitted_at":"2026-06-03T09:14:43Z","abstract_excerpt":"Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimized primarily for semantic relevance, but retrieving plausible passages does not guarantee correct query execution. We introduce QO-Bench, a diagnostic benchmark for query-operator question answering over typed event tuples. The benchmark covers 22,984 news articles and 614 corporate events across 18 query templates, evaluated on 785 questions. Each gold answer is deterministic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04646","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/2606.04646/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":"2606.04646","created_at":"2026-06-04T01:09:22.931615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04646v1","created_at":"2026-06-04T01:09:22.931615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04646","created_at":"2026-06-04T01:09:22.931615+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGI6SG4QDQVW","created_at":"2026-06-04T01:09:22.931615+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGI6SG4QDQVWA63Q","created_at":"2026-06-04T01:09:22.931615+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGI6SG4Q","created_at":"2026-06-04T01:09:22.931615+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/LGI6SG4QDQVWA63QSF2BPFQ5TY","json":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY.json","graph_json":"https://pith.science/api/pith-number/LGI6SG4QDQVWA63QSF2BPFQ5TY/graph.json","events_json":"https://pith.science/api/pith-number/LGI6SG4QDQVWA63QSF2BPFQ5TY/events.json","paper":"https://pith.science/paper/LGI6SG4Q"},"agent_actions":{"view_html":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY","download_json":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY.json","view_paper":"https://pith.science/paper/LGI6SG4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04646&json=true","fetch_graph":"https://pith.science/api/pith-number/LGI6SG4QDQVWA63QSF2BPFQ5TY/graph.json","fetch_events":"https://pith.science/api/pith-number/LGI6SG4QDQVWA63QSF2BPFQ5TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY/action/storage_attestation","attest_author":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY/action/author_attestation","sign_citation":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY/action/citation_signature","submit_replication":"https://pith.science/pith/LGI6SG4QDQVWA63QSF2BPFQ5TY/action/replication_record"}},"created_at":"2026-06-04T01:09:22.931615+00:00","updated_at":"2026-06-04T01:09:22.931615+00:00"}