{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BURG5PRHW6VPGDAFCIJCSHGHMS","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":"1b23ef03a9e3c8c03010f4bb4ec44a25da9ce095f3d658196f53eeed3abd4305","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T05:46:27Z","title_canon_sha256":"85a67b660ead61f98c0f67124d2958cc061de3c2f80a35d6841df398bde2c022"},"schema_version":"1.0","source":{"id":"2507.12806","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12806","created_at":"2026-07-05T11:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12806v2","created_at":"2026-07-05T11:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12806","created_at":"2026-07-05T11:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"BURG5PRHW6VP","created_at":"2026-07-05T11:47:26Z"},{"alias_kind":"pith_short_16","alias_value":"BURG5PRHW6VPGDAF","created_at":"2026-07-05T11:47:26Z"},{"alias_kind":"pith_short_8","alias_value":"BURG5PRH","created_at":"2026-07-05T11:47:26Z"}],"graph_snapshots":[{"event_id":"sha256:358901d937b753d7b1661d61541b395451a2c6a9fd99e1a8e38fbcb9bedba7fe","target":"graph","created_at":"2026-07-05T11:47:26Z","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/2507.12806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks and labor-intensive data collection, limiting practical assessment. We introduce MCPEval, an open-source Model Context Protocol (MCP)-based framework that automates end-to-end task generation and deep evaluation of LLM agents across diverse domains. MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines. Empirical results across five ","authors_text":"Caiming Xiong, Haolin Chen, Huan Wang, Jianguo Zhang, Jielin Qiu, Roshan Ram, Shelby Heinecke, Shiyu Wang, Silvio Savarese, Weiran Yao, Zhiwei Liu, Zuxin Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T05:46:27Z","title":"MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12806","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:fd63f330718ecafc0f410b417bd84f80f31306639cc7b5f5b188b7a070d2b030","target":"record","created_at":"2026-07-05T11:47:26Z","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":"1b23ef03a9e3c8c03010f4bb4ec44a25da9ce095f3d658196f53eeed3abd4305","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T05:46:27Z","title_canon_sha256":"85a67b660ead61f98c0f67124d2958cc061de3c2f80a35d6841df398bde2c022"},"schema_version":"1.0","source":{"id":"2507.12806","kind":"arxiv","version":2}},"canonical_sha256":"0d226ebe27b7aaf30c051212291cc764b9732db2c1462fbc4e7a8e6b5ac6219a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d226ebe27b7aaf30c051212291cc764b9732db2c1462fbc4e7a8e6b5ac6219a","first_computed_at":"2026-07-05T11:47:26.260875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:26.260875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t0ojMvDVRwDyJCOqZEN2MXYrpMSs89gfhllRXdLSPNs89rQI9zNO9LHaUQwzOXB0g9HxM4xSPpzTzJXmnYO+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:26.261387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12806","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd63f330718ecafc0f410b417bd84f80f31306639cc7b5f5b188b7a070d2b030","sha256:358901d937b753d7b1661d61541b395451a2c6a9fd99e1a8e38fbcb9bedba7fe"],"state_sha256":"0738566f44df871a04659b72adceaa2452b8e01ec25ff445ac96eca0640925e2"}