{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SGRHEJRNG6TEYFAIJSZW22MISZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2c487bfaaf6b41b6482e37792342e68b8713d19580a2a9872d177d3c0303327a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-29T06:26:01Z","title_canon_sha256":"360e576d39c9c6534444fc228fe9fef17c7cf7878acbd6e293a155376f00de4d"},"schema_version":"1.0","source":{"id":"2504.08756","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08756","created_at":"2026-07-05T11:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08756v2","created_at":"2026-07-05T11:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08756","created_at":"2026-07-05T11:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"SGRHEJRNG6TE","created_at":"2026-07-05T11:12:30Z"},{"alias_kind":"pith_short_16","alias_value":"SGRHEJRNG6TEYFAI","created_at":"2026-07-05T11:12:30Z"},{"alias_kind":"pith_short_8","alias_value":"SGRHEJRN","created_at":"2026-07-05T11:12:30Z"}],"graph_snapshots":[{"event_id":"sha256:114328651bb8ad7e4ad837cbfc904b7e99ecae3d70d0dc161070edfd49b01263","target":"graph","created_at":"2026-07-05T11:12:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.08756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daeyong Kwon, Jeongsoo Lee, Junnyeong Jeong, Kyohoon Jin, Minwoo Kim, Minwoo Sim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-29T06:26:01Z","title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08756","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9659970ab16de7ab3dc597dea596ab84b04cd0b3dbfc75f876191fe570db8c0c","target":"record","created_at":"2026-07-05T11:12:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2c487bfaaf6b41b6482e37792342e68b8713d19580a2a9872d177d3c0303327a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-29T06:26:01Z","title_canon_sha256":"360e576d39c9c6534444fc228fe9fef17c7cf7878acbd6e293a155376f00de4d"},"schema_version":"1.0","source":{"id":"2504.08756","kind":"arxiv","version":2}},"canonical_sha256":"91a272262d37a64c14084cb36d698896777d6ca5395634a88317ebab1ca6114b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91a272262d37a64c14084cb36d698896777d6ca5395634a88317ebab1ca6114b","first_computed_at":"2026-07-05T11:12:30.674922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:30.674922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2JqSqGJOQV3dgoS2OjavUFFThtVcfiJzi0BcjOGRuvlL3JrdwtkqppzpdYpHGWtel9Ui8tpaP/jpAD4MWA3pBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:30.675694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08756","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9659970ab16de7ab3dc597dea596ab84b04cd0b3dbfc75f876191fe570db8c0c","sha256:114328651bb8ad7e4ad837cbfc904b7e99ecae3d70d0dc161070edfd49b01263"],"state_sha256":"3e5eaaa73ca665ce599b1f5040e7e44bbaca70a354f11db153e10b6c033f0ffc"}