{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S7ZWDMJJRZMJJHJ4PN6GPCGQDQ","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":"5524da72a3112b8244f1ae0f8a3a5a37cf23b65e8e98e42d079411e23df23e5b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T06:05:45Z","title_canon_sha256":"9640970ab90786488dd37759c5585241bfe12ab57faedbfc95432ff54e3fe340"},"schema_version":"1.0","source":{"id":"2411.09972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09972","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09972v1","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09972","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"S7ZWDMJJRZMJ","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"S7ZWDMJJRZMJJHJ4","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"S7ZWDMJJ","created_at":"2026-07-05T09:35:56Z"}],"graph_snapshots":[{"event_id":"sha256:03bb77407ca5fa35e4630fb1d985b86c7f60d7081faf8c7fa8e7936206117475","target":"graph","created_at":"2026-07-05T09:35:56Z","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/2411.09972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditionally, offline datasets have been used to evaluate task-oriented dialogue (TOD) models. These datasets lack context awareness, making them suboptimal benchmarks for conversational systems. In contrast, user-agents, which are context-aware, can simulate the variability and unpredictability of human conversations, making them better alternatives as evaluators. Prior research has utilized large language models (LLMs) to develop user-agents. Our work builds upon this by using LLMs to create user-agents for the evaluation of TOD systems. This involves prompting an LLM, using in-context exam","authors_text":"Dilek Hakkani-Tur, Gokhan Tur, Ruiliang Lyu, Sizhe Zhou, Taaha Kazi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T06:05:45Z","title":"Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09972","kind":"arxiv","version":1},"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":"sha256:9891cf0c91bcb8fc1ca76af52496c691a5763aab2112bf262106bc0ef39d59d4","target":"record","created_at":"2026-07-05T09:35:56Z","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":"5524da72a3112b8244f1ae0f8a3a5a37cf23b65e8e98e42d079411e23df23e5b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T06:05:45Z","title_canon_sha256":"9640970ab90786488dd37759c5585241bfe12ab57faedbfc95432ff54e3fe340"},"schema_version":"1.0","source":{"id":"2411.09972","kind":"arxiv","version":1}},"canonical_sha256":"97f361b1298e58949d3c7b7c6788d01c2615389193fb374f4bfcdb6e69b3560b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97f361b1298e58949d3c7b7c6788d01c2615389193fb374f4bfcdb6e69b3560b","first_computed_at":"2026-07-05T09:35:56.602562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:56.602562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ah6VSc5hP4JZ2Zgn0NpR3yswo+SRop4ICzmz1dYdBwh9uO2oXiZ55xeCbIcjSHW3X3oWL/BCfAhaAkO+ZfOoBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:56.603062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9891cf0c91bcb8fc1ca76af52496c691a5763aab2112bf262106bc0ef39d59d4","sha256:03bb77407ca5fa35e4630fb1d985b86c7f60d7081faf8c7fa8e7936206117475"],"state_sha256":"660ffd3628994687579254c5790245b125ec636c99f4b9b6d3d38c571924a97e"}