{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YB5TQZ5JYL76M5RYG6JCJGOF4S","short_pith_number":"pith:YB5TQZ5J","schema_version":"1.0","canonical_sha256":"c07b3867a9c2ffe6763837922499c5e4b32870e44e00cf64d767748c78782aa6","source":{"kind":"arxiv","id":"2603.23160","version":2},"attestation_state":"computed","paper":{"title":"UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dun Pei, Guangtao Zhai, Haodong Zhao, Qi Jia, Shibo Wang, Xiangyang Zhu, Xiujie Song, Ye Shen, Zicheng Zhang, Zijian Chen","submitted_at":"2026-03-24T13:01:31Z","abstract_excerpt":"Benchmarking large language models (LLMs) and agents in multi-turn interactive scenarios is essential for understanding their practical capabilities. However, existing evaluation protocols are highly heterogeneous, differing significantly in dataset formats, model interfaces, and evaluation pipelines, which severely impedes systematic comparison. In this work, we present UniDial-EvalKit (UDE), a unified evaluation toolkit for assessing interactive AI systems. The core contribution of UDE lies in its holistic unification: it standardizes heterogeneous data formats into a universal schema, strea"},"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":"2603.23160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-24T13:01:31Z","cross_cats_sorted":[],"title_canon_sha256":"0d079e5049810b16dda2117e72acd93776bcbc465fd40661961cb84d2ba07c81","abstract_canon_sha256":"72ea3269446f0cf0bc45c9c4672af5b80d59430fd03cc3f5104c0441dc7068dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:38.104993Z","signature_b64":"k7BU3Ps+Di6R87kHAO7ILc0HN9ruzbQWAc2omxNJcuktYyljPsDO2KmOwlh+qGP+oKhNPIPoxFMgv1XxpKRIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c07b3867a9c2ffe6763837922499c5e4b32870e44e00cf64d767748c78782aa6","last_reissued_at":"2026-06-01T01:02:38.103749Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:38.103749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dun Pei, Guangtao Zhai, Haodong Zhao, Qi Jia, Shibo Wang, Xiangyang Zhu, Xiujie Song, Ye Shen, Zicheng Zhang, Zijian Chen","submitted_at":"2026-03-24T13:01:31Z","abstract_excerpt":"Benchmarking large language models (LLMs) and agents in multi-turn interactive scenarios is essential for understanding their practical capabilities. However, existing evaluation protocols are highly heterogeneous, differing significantly in dataset formats, model interfaces, and evaluation pipelines, which severely impedes systematic comparison. In this work, we present UniDial-EvalKit (UDE), a unified evaluation toolkit for assessing interactive AI systems. The core contribution of UDE lies in its holistic unification: it standardizes heterogeneous data formats into a universal schema, strea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23160","kind":"arxiv","version":2},"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/2603.23160/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":"2603.23160","created_at":"2026-06-01T01:02:38.103967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.23160v2","created_at":"2026-06-01T01:02:38.103967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23160","created_at":"2026-06-01T01:02:38.103967+00:00"},{"alias_kind":"pith_short_12","alias_value":"YB5TQZ5JYL76","created_at":"2026-06-01T01:02:38.103967+00:00"},{"alias_kind":"pith_short_16","alias_value":"YB5TQZ5JYL76M5RY","created_at":"2026-06-01T01:02:38.103967+00:00"},{"alias_kind":"pith_short_8","alias_value":"YB5TQZ5J","created_at":"2026-06-01T01:02:38.103967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S","json":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S.json","graph_json":"https://pith.science/api/pith-number/YB5TQZ5JYL76M5RYG6JCJGOF4S/graph.json","events_json":"https://pith.science/api/pith-number/YB5TQZ5JYL76M5RYG6JCJGOF4S/events.json","paper":"https://pith.science/paper/YB5TQZ5J"},"agent_actions":{"view_html":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S","download_json":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S.json","view_paper":"https://pith.science/paper/YB5TQZ5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.23160&json=true","fetch_graph":"https://pith.science/api/pith-number/YB5TQZ5JYL76M5RYG6JCJGOF4S/graph.json","fetch_events":"https://pith.science/api/pith-number/YB5TQZ5JYL76M5RYG6JCJGOF4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S/action/storage_attestation","attest_author":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S/action/author_attestation","sign_citation":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S/action/citation_signature","submit_replication":"https://pith.science/pith/YB5TQZ5JYL76M5RYG6JCJGOF4S/action/replication_record"}},"created_at":"2026-06-01T01:02:38.103967+00:00","updated_at":"2026-06-01T01:02:38.103967+00:00"}