{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z4UXEZ77YEBPBOHC3YDCJMH7N3","short_pith_number":"pith:Z4UXEZ77","schema_version":"1.0","canonical_sha256":"cf297267ffc102f0b8e2de0624b0ff6ee04aeff44c2d5629470d6c2e9a164433","source":{"kind":"arxiv","id":"2405.02178","version":2},"attestation_state":"computed","paper":{"title":"Assessing and Verifying Task Utility in LLM-Powered Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Charles L. A. Clarke, Chi Wang, Julia Kiseleva, Negar Arabzadeh, Nikhil Mehta, Qinqyun Wu, Siqing Huo","submitted_at":"2024-05-03T15:26:27Z","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 "},"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":"2405.02178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-03T15:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"419820760c31f7ab14f6c3a9c3f3eec34acbeaf81cfbc9f3d3675ae18652be31","abstract_canon_sha256":"5e92f5b2bb2e45fd96e9c7681cbd877edf6228c9f51d27e375684e8b40852b9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:08.248413Z","signature_b64":"8uleX4M3PyaCoTd+gzkI009vXD8vnH6fFiSpYMPGJM6CLVBUfeJzUnRUy3++fwGQMRijS228kXfQlQlc0OFAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf297267ffc102f0b8e2de0624b0ff6ee04aeff44c2d5629470d6c2e9a164433","last_reissued_at":"2026-07-05T08:18:08.247924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:08.247924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing and Verifying Task Utility in LLM-Powered Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Charles L. A. Clarke, Chi Wang, Julia Kiseleva, Negar Arabzadeh, Nikhil Mehta, Qinqyun Wu, Siqing Huo","submitted_at":"2024-05-03T15:26:27Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02178","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/2405.02178/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":"2405.02178","created_at":"2026-07-05T08:18:08.247975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02178v2","created_at":"2026-07-05T08:18:08.247975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02178","created_at":"2026-07-05T08:18:08.247975+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4UXEZ77YEBP","created_at":"2026-07-05T08:18:08.247975+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4UXEZ77YEBPBOHC","created_at":"2026-07-05T08:18:08.247975+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4UXEZ77","created_at":"2026-07-05T08:18:08.247975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3","json":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3.json","graph_json":"https://pith.science/api/pith-number/Z4UXEZ77YEBPBOHC3YDCJMH7N3/graph.json","events_json":"https://pith.science/api/pith-number/Z4UXEZ77YEBPBOHC3YDCJMH7N3/events.json","paper":"https://pith.science/paper/Z4UXEZ77"},"agent_actions":{"view_html":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3","download_json":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3.json","view_paper":"https://pith.science/paper/Z4UXEZ77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02178&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4UXEZ77YEBPBOHC3YDCJMH7N3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4UXEZ77YEBPBOHC3YDCJMH7N3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3/action/storage_attestation","attest_author":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3/action/author_attestation","sign_citation":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3/action/citation_signature","submit_replication":"https://pith.science/pith/Z4UXEZ77YEBPBOHC3YDCJMH7N3/action/replication_record"}},"created_at":"2026-07-05T08:18:08.247975+00:00","updated_at":"2026-07-05T08:18:08.247975+00:00"}