{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z4UXEZ77YEBPBOHC3YDCJMH7N3","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":"5e92f5b2bb2e45fd96e9c7681cbd877edf6228c9f51d27e375684e8b40852b9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-03T15:26:27Z","title_canon_sha256":"419820760c31f7ab14f6c3a9c3f3eec34acbeaf81cfbc9f3d3675ae18652be31"},"schema_version":"1.0","source":{"id":"2405.02178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02178","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02178v2","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02178","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z4UXEZ77YEBP","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z4UXEZ77YEBPBOHC","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z4UXEZ77","created_at":"2026-07-05T08:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:8077240eebff1515bd6b3f52fdd204cbb156a2a0d172d3042df319b1cf7f9fab","target":"graph","created_at":"2026-07-05T08:18:08Z","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/2405.02178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. However, a significant gap remains in assessing to what extent LLM-powered applications genuinely enhance user experience and task execution efficiency. This highlights the need to verify utility of LLM-powered applications, particularly by ensuring alignment between the application's functionality and end-user needs. We introduce AgentEval, a novel framework designed to simplify the utility verification process by ","authors_text":"Ahmed Awadallah, Charles L. A. Clarke, Chi Wang, Julia Kiseleva, Negar Arabzadeh, Nikhil Mehta, Qinqyun Wu, Siqing Huo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-03T15:26:27Z","title":"Assessing and Verifying Task Utility in LLM-Powered Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02178","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":"sha256:1c4802c29f59319fbfc61cf105b47194976d861b7e080ec559344182539b153c","target":"record","created_at":"2026-07-05T08:18:08Z","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":"5e92f5b2bb2e45fd96e9c7681cbd877edf6228c9f51d27e375684e8b40852b9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-03T15:26:27Z","title_canon_sha256":"419820760c31f7ab14f6c3a9c3f3eec34acbeaf81cfbc9f3d3675ae18652be31"},"schema_version":"1.0","source":{"id":"2405.02178","kind":"arxiv","version":2}},"canonical_sha256":"cf297267ffc102f0b8e2de0624b0ff6ee04aeff44c2d5629470d6c2e9a164433","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf297267ffc102f0b8e2de0624b0ff6ee04aeff44c2d5629470d6c2e9a164433","first_computed_at":"2026-07-05T08:18:08.247924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:08.247924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8uleX4M3PyaCoTd+gzkI009vXD8vnH6fFiSpYMPGJM6CLVBUfeJzUnRUy3++fwGQMRijS228kXfQlQlc0OFAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:08.248413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c4802c29f59319fbfc61cf105b47194976d861b7e080ec559344182539b153c","sha256:8077240eebff1515bd6b3f52fdd204cbb156a2a0d172d3042df319b1cf7f9fab"],"state_sha256":"5c994e475c200f67d49e843743c5f3742e9b9250c1b51783ec3771851efd9a87"}