{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R73442BU32X5YCWQF3A5D7CWGE","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":"79b662460fdf7cda191cd939e0b1fb7539dd7b5a0d559fb0312d3c65a62c7de7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T03:43:30Z","title_canon_sha256":"9e7d2eed643c55765afa5b0353a98a2b35c2f1432d6eac03231eda494b5a517d"},"schema_version":"1.0","source":{"id":"2505.11811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11811","created_at":"2026-07-05T11:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11811v1","created_at":"2026-07-05T11:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11811","created_at":"2026-07-05T11:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"R73442BU32X5","created_at":"2026-07-05T11:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"R73442BU32X5YCWQ","created_at":"2026-07-05T11:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"R73442BU","created_at":"2026-07-05T11:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:b0da3b973d000c985fa83dfa6c88796324d9468f919a09b740d5efaf93d34512","target":"graph","created_at":"2026-07-05T11:04:26Z","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/2505.11811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-hop question answering (QA) involves finding multiple relevant passages and performing step-by-step reasoning to answer complex questions. Previous works on multi-hop QA employ specific methods from different modeling perspectives based on large language models (LLMs), regardless of the question types. In this paper, we first conduct an in-depth analysis of public multi-hop QA benchmarks, dividing the questions into four types and evaluating five types of cutting-edge methods for multi-hop QA: Chain-of-Thought (CoT), Single-step, Iterative-step, Sub-step, and Adaptive-step. We find that ","authors_text":"Chengyu Wang, Dongyang Li, Qizhou Chen, Taolin Zhang, Xiaofeng He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T03:43:30Z","title":"BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11811","kind":"arxiv","version":1},"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:ea2b3d95cd3679a2209b5d2ce4f40948300d5bbe7547b7dc7150bb07e2ea5ca4","target":"record","created_at":"2026-07-05T11:04:26Z","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":"79b662460fdf7cda191cd939e0b1fb7539dd7b5a0d559fb0312d3c65a62c7de7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T03:43:30Z","title_canon_sha256":"9e7d2eed643c55765afa5b0353a98a2b35c2f1432d6eac03231eda494b5a517d"},"schema_version":"1.0","source":{"id":"2505.11811","kind":"arxiv","version":1}},"canonical_sha256":"8ff7ce6834deafdc0ad02ec1d1fc56310685fbe617ff5003141e8a35f9666497","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ff7ce6834deafdc0ad02ec1d1fc56310685fbe617ff5003141e8a35f9666497","first_computed_at":"2026-07-05T11:04:26.934653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:26.934653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HxkkiY4ynrG+4jguy2sqwpMa2lOKCWOgKghCZR4lG7NDUjjZCsaMgtwLMyqgYkuKiY8HqtzALXM1dotmcBXKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:26.935257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea2b3d95cd3679a2209b5d2ce4f40948300d5bbe7547b7dc7150bb07e2ea5ca4","sha256:b0da3b973d000c985fa83dfa6c88796324d9468f919a09b740d5efaf93d34512"],"state_sha256":"4bae299cc562bc7afedba22fa511a30a3bc776f740eb701f762a0c23650622e2"}