{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AIRPX2A7PGIMESTNLDSU7MGUUE","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":"cfc337d5c7f973666902600275cd45c02125de61cc5903450015de5a736f7882","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:21:59Z","title_canon_sha256":"b302e60c132b53a1bb2dc33fb364f04c1f115c43bb341c7d51e31e83763c9f26"},"schema_version":"1.0","source":{"id":"2402.14762","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14762","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14762v3","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14762","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"AIRPX2A7PGIM","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"AIRPX2A7PGIMESTN","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"AIRPX2A7","created_at":"2026-07-05T09:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:039f7e40b44d6b23e6434363796e14fc88ccba3cb33199808e2c5de449bacbd1","target":"graph","created_at":"2026-07-05T09:30:59Z","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/2402.14762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Large Language Models (LLMs) has drastically enhanced dialogue systems. However, comprehensively evaluating the dialogue abilities of LLMs remains a challenge. Previous benchmarks have primarily focused on single-turn dialogues or provided coarse-grained and incomplete assessments of multi-turn dialogues, overlooking the complexity and fine-grained nuances of real-life dialogues. To address this issue, we introduce MT-Bench-101, specifically designed to evaluate the fine-grained abilities of LLMs in multi-turn dialogues. By conducting a detailed analysis of real multi-turn dialog","authors_text":"Bo Zheng, Ge Bai, Jiaheng Liu, Jie Liu, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Xingyuan Bu, Yancheng He, Zhanhui Zhou, Zhuoran Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:21:59Z","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14762","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":"sha256:29c3e708671dcee7f9577d11f41c46b7eddf82d6f549f89f897e734a68204d59","target":"record","created_at":"2026-07-05T09:30:59Z","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":"cfc337d5c7f973666902600275cd45c02125de61cc5903450015de5a736f7882","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:21:59Z","title_canon_sha256":"b302e60c132b53a1bb2dc33fb364f04c1f115c43bb341c7d51e31e83763c9f26"},"schema_version":"1.0","source":{"id":"2402.14762","kind":"arxiv","version":3}},"canonical_sha256":"0222fbe81f7990c24a6d58e54fb0d4a139d0adfb2e40011d33e48bdb8d8ae521","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0222fbe81f7990c24a6d58e54fb0d4a139d0adfb2e40011d33e48bdb8d8ae521","first_computed_at":"2026-07-05T09:30:59.601677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:59.601677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C5IajbdC6F/lJChKo5JNqsXppeuSGTswIorScYk+3YgzIei+51/FtUSHJ2S+ju/vHo1lJ693ZlOsiqItL+jQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:59.602195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14762","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29c3e708671dcee7f9577d11f41c46b7eddf82d6f549f89f897e734a68204d59","sha256:039f7e40b44d6b23e6434363796e14fc88ccba3cb33199808e2c5de449bacbd1"],"state_sha256":"fc223994a14a312ae5b787f34a600accec05b9b485581d9b73efdea640cc0abf"}