{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:77ZKCHWIWGDEZFYEEWFAO7NFOM","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":"88607a6114159a6431e226363fc00ab82bbfa2ac560f8c9148a2e8b71665ccf8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","title_canon_sha256":"58f06f529d22d8fa2ea75e0d053d98f3dacb1432f21b9b386413edf44ea5f39c"},"schema_version":"1.0","source":{"id":"2311.01677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01677","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01677v2","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01677","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"77ZKCHWIWGDE","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_16","alias_value":"77ZKCHWIWGDEZFYE","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_8","alias_value":"77ZKCHWI","created_at":"2026-07-05T08:02:02Z"}],"graph_snapshots":[{"event_id":"sha256:ab323a1894e5bb4a2814ed0d183d679581e2ec5f595c9ddf772832e2acfea223","target":"graph","created_at":"2026-07-05T08:02:02Z","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/2311.01677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable breakthroughs in new dialogue capabilities by leveraging instruction tuning, which refreshes human impressions of dialogue systems. The long-standing goal of dialogue systems is to be human-like enough to establish long-term connections with users. Therefore, there has been an urgent need to evaluate LLMs as human-like dialogue systems. In this paper, we propose DialogBench, a dialogue evaluation benchmark that contains 12 dialogue tasks to probe the capabilities of LLMs as human-like dialogue systems should have. Specifically, we prompt GP","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Junda Lu, Kun Gai, Yihong Tang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01677","kind":"arxiv","version":2},"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":"sha256:191ad5750aa867b38d19e2510637f56d7e4487d8295939800b6d646ec3a528e4","target":"record","created_at":"2026-07-05T08:02:02Z","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":"88607a6114159a6431e226363fc00ab82bbfa2ac560f8c9148a2e8b71665ccf8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","title_canon_sha256":"58f06f529d22d8fa2ea75e0d053d98f3dacb1432f21b9b386413edf44ea5f39c"},"schema_version":"1.0","source":{"id":"2311.01677","kind":"arxiv","version":2}},"canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","first_computed_at":"2026-07-05T08:02:02.759062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:02.759062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yy6sIKMrYdeFZVgWPAg2lZP1Jhfc64cU9lrhZas/EagPaKd5y5dDcK4OpGD9hY3rBmLuUal76vuT/4HwC9GQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:02.759597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:191ad5750aa867b38d19e2510637f56d7e4487d8295939800b6d646ec3a528e4","sha256:ab323a1894e5bb4a2814ed0d183d679581e2ec5f595c9ddf772832e2acfea223"],"state_sha256":"0199ba026e0e706ea85f8e4bb15059f406cf6d85800430299d09e6ca73d8942a"}