{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWESIHK4I25GV45TFY2YFXSCKB","short_pith_number":"pith:UWESIHK4","schema_version":"1.0","canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","source":{"kind":"arxiv","id":"2602.03238","version":2},"attestation_state":"computed","paper":{"title":"The Necessity of a Unified Framework for LLM-Based Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Sun, Pengyu Zhu, Philip S. Yu, Sen Su","submitted_at":"2026-02-03T08:18:37Z","abstract_excerpt":"With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents presents unique challenges that distinguish them from static QA benchmarks. We observe that current agent benchmarks are heavily confounded by extraneous factors, including system prompts, toolset configurations, and environmental dynamics. Existing evaluations often rely on fragmented, researcher-specific frameworks where the prompt engineering for reasoning and tool usage varies significantly, making it difficult to attribute performance gains to the mo"},"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":"2602.03238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"6b9f6601b758fd4989528a6a76f4f467bebaa4a6f4002c1ba99af3653f25512f","abstract_canon_sha256":"e60bbfee8e9d7f3e90735638d357be2d4155f0c0c46fa90e8f460e59b2ff5e54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:43.835417Z","signature_b64":"fPcx8fO9Mb0y0YkiD1/N1tdH8ZWQkxZ/qcm/0GoZTYQMYsQuDEWAc095MkRud6DO6D6I4f1FP0cIYChpEdaHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","last_reissued_at":"2026-05-27T01:05:43.834687Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:43.834687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Necessity of a Unified Framework for LLM-Based Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Sun, Pengyu Zhu, Philip S. Yu, Sen Su","submitted_at":"2026-02-03T08:18:37Z","abstract_excerpt":"With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents presents unique challenges that distinguish them from static QA benchmarks. We observe that current agent benchmarks are heavily confounded by extraneous factors, including system prompts, toolset configurations, and environmental dynamics. Existing evaluations often rely on fragmented, researcher-specific frameworks where the prompt engineering for reasoning and tool usage varies significantly, making it difficult to attribute performance gains to the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03238","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/2602.03238/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":"2602.03238","created_at":"2026-05-27T01:05:43.834783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03238v2","created_at":"2026-05-27T01:05:43.834783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03238","created_at":"2026-05-27T01:05:43.834783+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWESIHK4I25G","created_at":"2026-05-27T01:05:43.834783+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWESIHK4I25GV45T","created_at":"2026-05-27T01:05:43.834783+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWESIHK4","created_at":"2026-05-27T01:05:43.834783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB","json":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB.json","graph_json":"https://pith.science/api/pith-number/UWESIHK4I25GV45TFY2YFXSCKB/graph.json","events_json":"https://pith.science/api/pith-number/UWESIHK4I25GV45TFY2YFXSCKB/events.json","paper":"https://pith.science/paper/UWESIHK4"},"agent_actions":{"view_html":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB","download_json":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB.json","view_paper":"https://pith.science/paper/UWESIHK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03238&json=true","fetch_graph":"https://pith.science/api/pith-number/UWESIHK4I25GV45TFY2YFXSCKB/graph.json","fetch_events":"https://pith.science/api/pith-number/UWESIHK4I25GV45TFY2YFXSCKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/action/storage_attestation","attest_author":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/action/author_attestation","sign_citation":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/action/citation_signature","submit_replication":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/action/replication_record"}},"created_at":"2026-05-27T01:05:43.834783+00:00","updated_at":"2026-05-27T01:05:43.834783+00:00"}