{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U6YJF2DT64FMYS5R3RXAUD6CRV","short_pith_number":"pith:U6YJF2DT","schema_version":"1.0","canonical_sha256":"a7b092e873f70acc4bb1dc6e0a0fc28d73535426cc3d6c6830700a349ae3e3e2","source":{"kind":"arxiv","id":"2607.20531","version":1},"attestation_state":"computed","paper":{"title":"DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aidar Shumbalov, Anna Kalyuzhnaya, Artem Kuznetsov, Ilya Galyukshev, Jerzy Kami\\'nski, Kirill Redko, Sergey Chuprin","submitted_at":"2026-07-10T12:25:57Z","abstract_excerpt":"Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed \"ground-truth\" list of tools, both of which are fragile once the underlying data is live and stateful. We present DynamicMCPBench, a reusable framework rather than a fixed dataset. A practitioner can run it on their own MCP servers to test models on their own tasks, or let it collect servers automatically to measure a model's general ability to solve agentic tasks. Given the servers and any set of models, it generates "},"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":"2607.20531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T12:25:57Z","cross_cats_sorted":[],"title_canon_sha256":"eb9720f77b7408a0ccf062584f89e92076ce49a290de63eba317790b2c6a4e98","abstract_canon_sha256":"80104e4593040c2942c821392571d05b437fca62b66736aa23c2bfddcbab5064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:20.659944Z","signature_b64":"IyqBnouwJu+v4Yy/xYLz7ccin19b40pgC70kYBXniCSI2FG0Rex6345ar9/iEVLVz0kOOscl5dvsXzx+eUK8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b092e873f70acc4bb1dc6e0a0fc28d73535426cc3d6c6830700a349ae3e3e2","last_reissued_at":"2026-07-24T00:23:20.659059Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:20.659059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aidar Shumbalov, Anna Kalyuzhnaya, Artem Kuznetsov, Ilya Galyukshev, Jerzy Kami\\'nski, Kirill Redko, Sergey Chuprin","submitted_at":"2026-07-10T12:25:57Z","abstract_excerpt":"Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed \"ground-truth\" list of tools, both of which are fragile once the underlying data is live and stateful. We present DynamicMCPBench, a reusable framework rather than a fixed dataset. A practitioner can run it on their own MCP servers to test models on their own tasks, or let it collect servers automatically to measure a model's general ability to solve agentic tasks. Given the servers and any set of models, it generates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20531","kind":"arxiv","version":1},"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/2607.20531/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":"2607.20531","created_at":"2026-07-24T00:23:20.659523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20531v1","created_at":"2026-07-24T00:23:20.659523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20531","created_at":"2026-07-24T00:23:20.659523+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6YJF2DT64FM","created_at":"2026-07-24T00:23:20.659523+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6YJF2DT64FMYS5R","created_at":"2026-07-24T00:23:20.659523+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6YJF2DT","created_at":"2026-07-24T00:23:20.659523+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/U6YJF2DT64FMYS5R3RXAUD6CRV","json":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV.json","graph_json":"https://pith.science/api/pith-number/U6YJF2DT64FMYS5R3RXAUD6CRV/graph.json","events_json":"https://pith.science/api/pith-number/U6YJF2DT64FMYS5R3RXAUD6CRV/events.json","paper":"https://pith.science/paper/U6YJF2DT"},"agent_actions":{"view_html":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV","download_json":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV.json","view_paper":"https://pith.science/paper/U6YJF2DT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20531&json=true","fetch_graph":"https://pith.science/api/pith-number/U6YJF2DT64FMYS5R3RXAUD6CRV/graph.json","fetch_events":"https://pith.science/api/pith-number/U6YJF2DT64FMYS5R3RXAUD6CRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV/action/storage_attestation","attest_author":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV/action/author_attestation","sign_citation":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV/action/citation_signature","submit_replication":"https://pith.science/pith/U6YJF2DT64FMYS5R3RXAUD6CRV/action/replication_record"}},"created_at":"2026-07-24T00:23:20.659523+00:00","updated_at":"2026-07-24T00:23:20.659523+00:00"}