{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IS7AL2KED4TUUE7WV55TLOTXMF","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":"552bd0cffc9d1114bbae515560fa9914b526c4808b0aad0e3b7031e7b3bf10e7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T17:55:54Z","title_canon_sha256":"5be0f71daee13bc3499d7f0e273bb4225ae46185a20a3576a980167df0ec0b17"},"schema_version":"1.0","source":{"id":"2508.15760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15760","created_at":"2026-05-26T01:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15760v2","created_at":"2026-05-26T01:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15760","created_at":"2026-05-26T01:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"IS7AL2KED4TU","created_at":"2026-05-26T01:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"IS7AL2KED4TUUE7W","created_at":"2026-05-26T01:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"IS7AL2KE","created_at":"2026-05-26T01:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:80998b81d30de6ca3843731166d4a692c6e4ea2bc542b19d6708ee109b2cb534","target":"graph","created_at":"2026-05-26T01:02:27Z","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/2508.15760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, provider-specific tool definitions, the Model Context Protocol (MCP) offers a unified interface to discover and invoke tools dynamically. However, there is a significant gap in benchmarking multi-step tasks using diverse MCP tools in realistic, dynamic scenarios. In this work, we present LiveMCP-101, a benchmark of 101 real-world queries that require coordinated use of multiple MCP tools. To address temporal variability in real-world tool responses, we intro","authors_text":"Dinghan Shen, Jianbing Han, Kaiqiang Song, Mian Zhang, Ming Yin, Sathish Reddy Indurthi, Shujian Liu, Silei Xu, Simin Ma, Sixun Dong, Song Wang, Xun Wang, Yebowen Hu, Yiran Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T17:55:54Z","title":"LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15760","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":"sha256:60ddaaf10aff337031626abf1324a0028bd72d15fb0f0f68eb9ec34d5a892baa","target":"record","created_at":"2026-05-26T01:02:27Z","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":"552bd0cffc9d1114bbae515560fa9914b526c4808b0aad0e3b7031e7b3bf10e7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T17:55:54Z","title_canon_sha256":"5be0f71daee13bc3499d7f0e273bb4225ae46185a20a3576a980167df0ec0b17"},"schema_version":"1.0","source":{"id":"2508.15760","kind":"arxiv","version":2}},"canonical_sha256":"44be05e9441f274a13f6af7b35ba776179d4976890d3f473d33afd85e5243fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44be05e9441f274a13f6af7b35ba776179d4976890d3f473d33afd85e5243fc2","first_computed_at":"2026-05-26T01:02:27.452907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:27.452907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n52C/H80eveealDWxJjSprw0IMiJcE3vO9bpeZG5OGhgJg3Gsvx1Goh1uH6b7ugQ+GDVYptUEtnrdez5vsuwCA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:27.453815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60ddaaf10aff337031626abf1324a0028bd72d15fb0f0f68eb9ec34d5a892baa","sha256:80998b81d30de6ca3843731166d4a692c6e4ea2bc542b19d6708ee109b2cb534"],"state_sha256":"927b6fd59912f9be261afc1d8dba1bcda8e5b127054d182d9718955ae45ab239"}