{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFIQGDKVCJIRROUXW4D5IJZMCP","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":"9faae829310827201e84c62af1e5f7e5398f4c7525ddc1c015576ae3fe54b52f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T17:59:12Z","title_canon_sha256":"7ed84db062e43be59b7efb8e8ec21150decfb4b7b6519dff155df866451659db"},"schema_version":"1.0","source":{"id":"2505.17123","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17123","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17123v3","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17123","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"JFIQGDKVCJIR","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"JFIQGDKVCJIRROUX","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"JFIQGDKV","created_at":"2026-05-22T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:54ef5ba750eed2f02c7d0da96bb7b7e2833094592c736e499e42c93e69b4e649","target":"graph","created_at":"2026-05-22T01:03:42Z","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/2505.17123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dayiheng Liu, Fuli Feng, Keqin Bao, Moxin Li, Rui Men, Wenjie Wang, Xiaoyuan Li, Yichang Zhang, Yubo Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T17:59:12Z","title":"MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17123","kind":"arxiv","version":3},"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":"sha256:18f0cb2e6745bc5ae6c4a58b3b2528bf374acd4d92840cedc153024120467408","target":"record","created_at":"2026-05-22T01:03:42Z","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":"9faae829310827201e84c62af1e5f7e5398f4c7525ddc1c015576ae3fe54b52f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T17:59:12Z","title_canon_sha256":"7ed84db062e43be59b7efb8e8ec21150decfb4b7b6519dff155df866451659db"},"schema_version":"1.0","source":{"id":"2505.17123","kind":"arxiv","version":3}},"canonical_sha256":"4951030d55125118ba97b707d4272c13c8f63e895f8c1cc6eb9a5e06103ffc44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4951030d55125118ba97b707d4272c13c8f63e895f8c1cc6eb9a5e06103ffc44","first_computed_at":"2026-05-22T01:03:42.964847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:42.964847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Te33WHXK/nrITaJcvUU86465ILxXm5uMx/GcI4jBBeIO9sbf+DX7RfPXwj2/By6X/IB7TX0/SbLJyl6PUl+RCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:42.965766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17123","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18f0cb2e6745bc5ae6c4a58b3b2528bf374acd4d92840cedc153024120467408","sha256:54ef5ba750eed2f02c7d0da96bb7b7e2833094592c736e499e42c93e69b4e649"],"state_sha256":"a574f507f63088fa8e810c0964f4f6ec8deccaaa9eaacc2b4dd20240afec502b"}