{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4EHPZXA5KD4T45MKT6Z3Q3UFP","short_pith_number":"pith:B4EHPZXA","schema_version":"1.0","canonical_sha256":"0f0877e6e0ea87c9f3ac54fd9dc3742bc4b7bff9350222632609d98ecb733561","source":{"kind":"arxiv","id":"2410.06062","version":4},"attestation_state":"computed","paper":{"title":"LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Ana Claudia Sima, Jerven Bolleman, Severine Duvaud, Tarcisio Mendes de Farias, Vincent Emonet","submitted_at":"2024-10-08T14:09:12Z","abstract_excerpt":"We introduce a Retrieval-Augmented Generation (RAG) system for translating user questions into accurate federated SPARQL queries over bioinformatics knowledge graphs (KGs) leveraging Large Language Models (LLMs). To enhance accuracy and reduce hallucinations in query generation, our system utilises metadata from the KGs, including query examples and schema information, and incorporates a validation step to correct generated queries. The system is available online at chat.expasy.org."},"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":"2410.06062","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-08T14:09:12Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"43728f81d33e5bf25a3efe1b70b20ca8742175827d865deb2fa84d8158b59ef3","abstract_canon_sha256":"9330d99d85afec4acbae2886397641be8922df7790c7c8502453f20e8582acb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:01.458013Z","signature_b64":"RS30U9ypUVhlEPGJpDRhstV1wkqayOa+ifXy0McF6AIn/rWu8A+GncLbLLxM31k8/daxqsGK0o+BLW7GBe6yAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f0877e6e0ea87c9f3ac54fd9dc3742bc4b7bff9350222632609d98ecb733561","last_reissued_at":"2026-07-05T10:12:01.457517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:01.457517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Ana Claudia Sima, Jerven Bolleman, Severine Duvaud, Tarcisio Mendes de Farias, Vincent Emonet","submitted_at":"2024-10-08T14:09:12Z","abstract_excerpt":"We introduce a Retrieval-Augmented Generation (RAG) system for translating user questions into accurate federated SPARQL queries over bioinformatics knowledge graphs (KGs) leveraging Large Language Models (LLMs). To enhance accuracy and reduce hallucinations in query generation, our system utilises metadata from the KGs, including query examples and schema information, and incorporates a validation step to correct generated queries. The system is available online at chat.expasy.org."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06062","kind":"arxiv","version":4},"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/2410.06062/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":"2410.06062","created_at":"2026-07-05T10:12:01.457576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06062v4","created_at":"2026-07-05T10:12:01.457576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06062","created_at":"2026-07-05T10:12:01.457576+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4EHPZXA5KD4","created_at":"2026-07-05T10:12:01.457576+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4EHPZXA5KD4T45M","created_at":"2026-07-05T10:12:01.457576+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4EHPZXA","created_at":"2026-07-05T10:12:01.457576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00203","citing_title":"DeSQ: Decomposition-based SPARQL Query Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17617","citing_title":"GraphMind: From Operational Traces to Self-Evolving Workflow Automation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30283","citing_title":"mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16014","citing_title":"MUSEKG: A Knowledge Graph Over Museum Collections","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17617","citing_title":"GraphMind: From Operational Traces to Self-Evolving Workflow Automation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02545","citing_title":"Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP","json":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP.json","graph_json":"https://pith.science/api/pith-number/B4EHPZXA5KD4T45MKT6Z3Q3UFP/graph.json","events_json":"https://pith.science/api/pith-number/B4EHPZXA5KD4T45MKT6Z3Q3UFP/events.json","paper":"https://pith.science/paper/B4EHPZXA"},"agent_actions":{"view_html":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP","download_json":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP.json","view_paper":"https://pith.science/paper/B4EHPZXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06062&json=true","fetch_graph":"https://pith.science/api/pith-number/B4EHPZXA5KD4T45MKT6Z3Q3UFP/graph.json","fetch_events":"https://pith.science/api/pith-number/B4EHPZXA5KD4T45MKT6Z3Q3UFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP/action/storage_attestation","attest_author":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP/action/author_attestation","sign_citation":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP/action/citation_signature","submit_replication":"https://pith.science/pith/B4EHPZXA5KD4T45MKT6Z3Q3UFP/action/replication_record"}},"created_at":"2026-07-05T10:12:01.457576+00:00","updated_at":"2026-07-05T10:12:01.457576+00:00"}