{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:77ZKCHWIWGDEZFYEEWFAO7NFOM","short_pith_number":"pith:77ZKCHWI","canonical_record":{"source":{"id":"2311.01677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58f06f529d22d8fa2ea75e0d053d98f3dacb1432f21b9b386413edf44ea5f39c","abstract_canon_sha256":"88607a6114159a6431e226363fc00ab82bbfa2ac560f8c9148a2e8b71665ccf8"},"schema_version":"1.0"},"canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","source":{"kind":"arxiv","id":"2311.01677","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:77ZKCHWIWGDEZFYEEWFAO7NFOM","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58f06f529d22d8fa2ea75e0d053d98f3dacb1432f21b9b386413edf44ea5f39c","abstract_canon_sha256":"88607a6114159a6431e226363fc00ab82bbfa2ac560f8c9148a2e8b71665ccf8"},"schema_version":"1.0"},"canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:02.759597Z","signature_b64":"yy6sIKMrYdeFZVgWPAg2lZP1Jhfc64cU9lrhZas/EagPaKd5y5dDcK4OpGD9hY3rBmLuUal76vuT/4HwC9GQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","last_reissued_at":"2026-07-05T08:02:02.759062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:02.759062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01677","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c5X0HcM91QxJZLZmnDkrb+SUz+mq5Dyt8BXyZVYAvmdt480U+NyxqzCSnezS9WG4nJQJ88e4+cC/Oi0csDVBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:46:16.741593Z"},"content_sha256":"191ad5750aa867b38d19e2510637f56d7e4487d8295939800b6d646ec3a528e4","schema_version":"1.0","event_id":"sha256:191ad5750aa867b38d19e2510637f56d7e4487d8295939800b6d646ec3a528e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:77ZKCHWIWGDEZFYEEWFAO7NFOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Junda Lu, Kun Gai, Yihong Tang","submitted_at":"2023-11-03T02:59:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01677","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/2311.01677/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBHOPMfW8lGjfCky/5akW4ODTfvKySK7R6G2QJmzdzQGu+0v1OyD63tbsERqlj4/W2dXrqCYxqzgAJu6N0fpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:46:16.742109Z"},"content_sha256":"ab323a1894e5bb4a2814ed0d183d679581e2ec5f595c9ddf772832e2acfea223","schema_version":"1.0","event_id":"sha256:ab323a1894e5bb4a2814ed0d183d679581e2ec5f595c9ddf772832e2acfea223"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/bundle.json","state_url":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T09:46:16Z","links":{"resolver":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM","bundle":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/bundle.json","state":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dh7Yf4iZji8tEozY8knr9nGka6ywBFZdIBE+9jiYU27LB3UoGDcsOYRpjEIhPcB2O8rtEiak88QpsOsE0bk8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:46:16.746882Z","bundle_sha256":"777cb92a24584479623eaf591e7a521b9e618171c53f5f54ae850956e2713e80"}}