{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4TGS3JHW3KCYVQRXSRPYFHCTHD","short_pith_number":"pith:4TGS3JHW","schema_version":"1.0","canonical_sha256":"e4cd2da4f6da858ac237945f829c5338d4fdf7cb7b784c145b4d4378c8d22102","source":{"kind":"arxiv","id":"2607.14561","version":1},"attestation_state":"computed","paper":{"title":"MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Axel-Cyrille Ngonga Ngomo, Daniel Vollmers, Hamada M. Zahera, Nikit Srivastava, Nikolaos Karalis, Ren\\'e Speck","submitted_at":"2026-07-16T04:40:05Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combining knowledge graphs (KGs) with LLMs facilitates the use of explicit symbolic knowledge that can be continuously updated without costly fine-tuning, while benefiting from rapidly advancing LLM reasoning. We propose MARS, a scalable knowledge graph question answering (KGQA) approach that requires no model fine-tuning. Rather than relying on open-ended agentic exploration, MARS per"},"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":"2607.14561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T04:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"b84f3306feed810d0dfbddbf130992d50a4e975bde8352ab1ddffd4cacf93769","abstract_canon_sha256":"ce2c2b39e757f58a795731cf1d7de74a6cdd08c579a70809f3d065d2d125a358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:18.319353Z","signature_b64":"qoXPi5o39cRrshNvo49npAHmo2DYsWLv0nr7P1OuGilIqthJ0YZ/opBRobVQr6CRWxGtWYBuzVC/afenC2U1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4cd2da4f6da858ac237945f829c5338d4fdf7cb7b784c145b4d4378c8d22102","last_reissued_at":"2026-07-17T01:21:18.318549Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:18.318549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Axel-Cyrille Ngonga Ngomo, Daniel Vollmers, Hamada M. Zahera, Nikit Srivastava, Nikolaos Karalis, Ren\\'e Speck","submitted_at":"2026-07-16T04:40:05Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combining knowledge graphs (KGs) with LLMs facilitates the use of explicit symbolic knowledge that can be continuously updated without costly fine-tuning, while benefiting from rapidly advancing LLM reasoning. We propose MARS, a scalable knowledge graph question answering (KGQA) approach that requires no model fine-tuning. Rather than relying on open-ended agentic exploration, MARS per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14561","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/2607.14561/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":"2607.14561","created_at":"2026-07-17T01:21:18.318960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14561v1","created_at":"2026-07-17T01:21:18.318960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14561","created_at":"2026-07-17T01:21:18.318960+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TGS3JHW3KCY","created_at":"2026-07-17T01:21:18.318960+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TGS3JHW3KCYVQRX","created_at":"2026-07-17T01:21:18.318960+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TGS3JHW","created_at":"2026-07-17T01:21:18.318960+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/4TGS3JHW3KCYVQRXSRPYFHCTHD","json":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD.json","graph_json":"https://pith.science/api/pith-number/4TGS3JHW3KCYVQRXSRPYFHCTHD/graph.json","events_json":"https://pith.science/api/pith-number/4TGS3JHW3KCYVQRXSRPYFHCTHD/events.json","paper":"https://pith.science/paper/4TGS3JHW"},"agent_actions":{"view_html":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD","download_json":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD.json","view_paper":"https://pith.science/paper/4TGS3JHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14561&json=true","fetch_graph":"https://pith.science/api/pith-number/4TGS3JHW3KCYVQRXSRPYFHCTHD/graph.json","fetch_events":"https://pith.science/api/pith-number/4TGS3JHW3KCYVQRXSRPYFHCTHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD/action/storage_attestation","attest_author":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD/action/author_attestation","sign_citation":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD/action/citation_signature","submit_replication":"https://pith.science/pith/4TGS3JHW3KCYVQRXSRPYFHCTHD/action/replication_record"}},"created_at":"2026-07-17T01:21:18.318960+00:00","updated_at":"2026-07-17T01:21:18.318960+00:00"}