{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S7C5J53ZYT3Q3NWAYGMBF7AOYY","short_pith_number":"pith:S7C5J53Z","schema_version":"1.0","canonical_sha256":"97c5d4f779c4f70db6c0c19812fc0ec636354e18f53ecfc4fda6b25707b601e3","source":{"kind":"arxiv","id":"2406.00562","version":1},"attestation_state":"computed","paper":{"title":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Farhad Ghassemi, Heidi C. Zhang, Jialiang Xu, Monica S. Lam, Shicheng Liu, Sina J. Semnani","submitted_at":"2024-06-01T21:54:09Z","abstract_excerpt":"We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge base, text, tables, and infoboxes. Our LLM-augmented approach achieves state-of-the-art performance on the Compmix dataset, the most comprehensive heterogeneous open-domain QA dataset, with 56.5% exact match (EM) rate. More importantly, manual analysis on a sample of the dataset suggests that SPAGHETTI is more than 90% accurate, indicating that EM"},"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":"2406.00562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-01T21:54:09Z","cross_cats_sorted":[],"title_canon_sha256":"a0b8f5ba4799222f354c41bf8b710d1d86211b79d90eaeb0f42114ee556944ba","abstract_canon_sha256":"5f3133d72f6a5e967815f6feaca151719132025a76e4395b4363adc7700eb755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:27.295681Z","signature_b64":"hibN5YbaZM4Bm2uoLk4MpIyUveeCE1vBV23xYGuWr4pPN3egQkrkkOBzG882sVSz3F74Zs13/Nclt1tcpdcMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c5d4f779c4f70db6c0c19812fc0ec636354e18f53ecfc4fda6b25707b601e3","last_reissued_at":"2026-07-05T08:26:27.295135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:27.295135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Farhad Ghassemi, Heidi C. Zhang, Jialiang Xu, Monica S. Lam, Shicheng Liu, Sina J. Semnani","submitted_at":"2024-06-01T21:54:09Z","abstract_excerpt":"We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge base, text, tables, and infoboxes. Our LLM-augmented approach achieves state-of-the-art performance on the Compmix dataset, the most comprehensive heterogeneous open-domain QA dataset, with 56.5% exact match (EM) rate. More importantly, manual analysis on a sample of the dataset suggests that SPAGHETTI is more than 90% accurate, indicating that EM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00562","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/2406.00562/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":"2406.00562","created_at":"2026-07-05T08:26:27.295204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00562v1","created_at":"2026-07-05T08:26:27.295204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00562","created_at":"2026-07-05T08:26:27.295204+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7C5J53ZYT3Q","created_at":"2026-07-05T08:26:27.295204+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7C5J53ZYT3Q3NWA","created_at":"2026-07-05T08:26:27.295204+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7C5J53Z","created_at":"2026-07-05T08:26:27.295204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16220","citing_title":"DBRouting: Routing End User Queries to Databases for Answerability","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY","json":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY.json","graph_json":"https://pith.science/api/pith-number/S7C5J53ZYT3Q3NWAYGMBF7AOYY/graph.json","events_json":"https://pith.science/api/pith-number/S7C5J53ZYT3Q3NWAYGMBF7AOYY/events.json","paper":"https://pith.science/paper/S7C5J53Z"},"agent_actions":{"view_html":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY","download_json":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY.json","view_paper":"https://pith.science/paper/S7C5J53Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00562&json=true","fetch_graph":"https://pith.science/api/pith-number/S7C5J53ZYT3Q3NWAYGMBF7AOYY/graph.json","fetch_events":"https://pith.science/api/pith-number/S7C5J53ZYT3Q3NWAYGMBF7AOYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY/action/storage_attestation","attest_author":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY/action/author_attestation","sign_citation":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY/action/citation_signature","submit_replication":"https://pith.science/pith/S7C5J53ZYT3Q3NWAYGMBF7AOYY/action/replication_record"}},"created_at":"2026-07-05T08:26:27.295204+00:00","updated_at":"2026-07-05T08:26:27.295204+00:00"}