{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SGRHEJRNG6TEYFAIJSZW22MISZ","short_pith_number":"pith:SGRHEJRN","schema_version":"1.0","canonical_sha256":"91a272262d37a64c14084cb36d698896777d6ca5395634a88317ebab1ca6114b","source":{"kind":"arxiv","id":"2504.08756","version":2},"attestation_state":"computed","paper":{"title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Daeyong Kwon, Jeongsoo Lee, Junnyeong Jeong, Kyohoon Jin, Minwoo Kim, Minwoo Sim","submitted_at":"2025-03-29T06:26:01Z","abstract_excerpt":"Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which capturing the complexity of reasoning based on hops and the distribution of supporting evidence. In this paper, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leveraging a multi-hop tree structure to generate logically connected, multi-chunk queries. Our fine-grai"},"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":"2504.08756","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-29T06:26:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"360e576d39c9c6534444fc228fe9fef17c7cf7878acbd6e293a155376f00de4d","abstract_canon_sha256":"2c487bfaaf6b41b6482e37792342e68b8713d19580a2a9872d177d3c0303327a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:30.675694Z","signature_b64":"2JqSqGJOQV3dgoS2OjavUFFThtVcfiJzi0BcjOGRuvlL3JrdwtkqppzpdYpHGWtel9Ui8tpaP/jpAD4MWA3pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a272262d37a64c14084cb36d698896777d6ca5395634a88317ebab1ca6114b","last_reissued_at":"2026-07-05T11:12:30.674922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:30.674922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Daeyong Kwon, Jeongsoo Lee, Junnyeong Jeong, Kyohoon Jin, Minwoo Kim, Minwoo Sim","submitted_at":"2025-03-29T06:26:01Z","abstract_excerpt":"Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which capturing the complexity of reasoning based on hops and the distribution of supporting evidence. In this paper, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leveraging a multi-hop tree structure to generate logically connected, multi-chunk queries. Our fine-grai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08756","kind":"arxiv","version":2},"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/2504.08756/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":"2504.08756","created_at":"2026-07-05T11:12:30.675145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08756v2","created_at":"2026-07-05T11:12:30.675145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08756","created_at":"2026-07-05T11:12:30.675145+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGRHEJRNG6TE","created_at":"2026-07-05T11:12:30.675145+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGRHEJRNG6TEYFAI","created_at":"2026-07-05T11:12:30.675145+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGRHEJRN","created_at":"2026-07-05T11:12:30.675145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23139","citing_title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ","json":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ.json","graph_json":"https://pith.science/api/pith-number/SGRHEJRNG6TEYFAIJSZW22MISZ/graph.json","events_json":"https://pith.science/api/pith-number/SGRHEJRNG6TEYFAIJSZW22MISZ/events.json","paper":"https://pith.science/paper/SGRHEJRN"},"agent_actions":{"view_html":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ","download_json":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ.json","view_paper":"https://pith.science/paper/SGRHEJRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08756&json=true","fetch_graph":"https://pith.science/api/pith-number/SGRHEJRNG6TEYFAIJSZW22MISZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SGRHEJRNG6TEYFAIJSZW22MISZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ/action/storage_attestation","attest_author":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ/action/author_attestation","sign_citation":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ/action/citation_signature","submit_replication":"https://pith.science/pith/SGRHEJRNG6TEYFAIJSZW22MISZ/action/replication_record"}},"created_at":"2026-07-05T11:12:30.675145+00:00","updated_at":"2026-07-05T11:12:30.675145+00:00"}