{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JFIQGDKVCJIRROUXW4D5IJZMCP","short_pith_number":"pith:JFIQGDKV","schema_version":"1.0","canonical_sha256":"4951030d55125118ba97b707d4272c13c8f63e895f8c1cc6eb9a5e06103ffc44","source":{"kind":"arxiv","id":"2505.17123","version":3},"attestation_state":"computed","paper":{"title":"MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Fuli Feng, Keqin Bao, Moxin Li, Rui Men, Wenjie Wang, Xiaoyuan Li, Yichang Zhang, Yubo Ma","submitted_at":"2025-05-21T17:59:12Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. However, current evaluations predominantly focus on single-turn reasoning scenarios, leaving interactive tasks largely unexplored. We attribute it to the absence of comprehensive datasets and scalable automatic evaluation protocols. To fill these gaps, we present MTR-Bench for LLMs' Multi-Turn Reasoning evaluation. Comprising 4 classes, 40 tasks, and 3600 instances, MTR-Bench covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions"},"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":"2505.17123","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T17:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"7ed84db062e43be59b7efb8e8ec21150decfb4b7b6519dff155df866451659db","abstract_canon_sha256":"9faae829310827201e84c62af1e5f7e5398f4c7525ddc1c015576ae3fe54b52f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:42.965766Z","signature_b64":"Te33WHXK/nrITaJcvUU86465ILxXm5uMx/GcI4jBBeIO9sbf+DX7RfPXwj2/By6X/IB7TX0/SbLJyl6PUl+RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4951030d55125118ba97b707d4272c13c8f63e895f8c1cc6eb9a5e06103ffc44","last_reissued_at":"2026-05-22T01:03:42.964847Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:42.964847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Fuli Feng, Keqin Bao, Moxin Li, Rui Men, Wenjie Wang, Xiaoyuan Li, Yichang Zhang, Yubo Ma","submitted_at":"2025-05-21T17:59:12Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. However, current evaluations predominantly focus on single-turn reasoning scenarios, leaving interactive tasks largely unexplored. We attribute it to the absence of comprehensive datasets and scalable automatic evaluation protocols. To fill these gaps, we present MTR-Bench for LLMs' Multi-Turn Reasoning evaluation. Comprising 4 classes, 40 tasks, and 3600 instances, MTR-Bench covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17123","kind":"arxiv","version":3},"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/2505.17123/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":"2505.17123","created_at":"2026-05-22T01:03:42.964981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17123v3","created_at":"2026-05-22T01:03:42.964981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17123","created_at":"2026-05-22T01:03:42.964981+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFIQGDKVCJIR","created_at":"2026-05-22T01:03:42.964981+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFIQGDKVCJIRROUX","created_at":"2026-05-22T01:03:42.964981+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFIQGDKV","created_at":"2026-05-22T01:03:42.964981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.10693","citing_title":"FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07549","citing_title":"EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP","json":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP.json","graph_json":"https://pith.science/api/pith-number/JFIQGDKVCJIRROUXW4D5IJZMCP/graph.json","events_json":"https://pith.science/api/pith-number/JFIQGDKVCJIRROUXW4D5IJZMCP/events.json","paper":"https://pith.science/paper/JFIQGDKV"},"agent_actions":{"view_html":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP","download_json":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP.json","view_paper":"https://pith.science/paper/JFIQGDKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17123&json=true","fetch_graph":"https://pith.science/api/pith-number/JFIQGDKVCJIRROUXW4D5IJZMCP/graph.json","fetch_events":"https://pith.science/api/pith-number/JFIQGDKVCJIRROUXW4D5IJZMCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP/action/storage_attestation","attest_author":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP/action/author_attestation","sign_citation":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP/action/citation_signature","submit_replication":"https://pith.science/pith/JFIQGDKVCJIRROUXW4D5IJZMCP/action/replication_record"}},"created_at":"2026-05-22T01:03:42.964981+00:00","updated_at":"2026-05-22T01:03:42.964981+00:00"}