{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U6YJF2DT64FMYS5R3RXAUD6CRV","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":"80104e4593040c2942c821392571d05b437fca62b66736aa23c2bfddcbab5064","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T12:25:57Z","title_canon_sha256":"eb9720f77b7408a0ccf062584f89e92076ce49a290de63eba317790b2c6a4e98"},"schema_version":"1.0","source":{"id":"2607.20531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20531","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20531v1","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20531","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"U6YJF2DT64FM","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"U6YJF2DT64FMYS5R","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"U6YJF2DT","created_at":"2026-07-24T00:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:0a478be51b140bd756ab2dd287d61b4abf1d44f297d05f328ce4d67458c4ddd1","target":"graph","created_at":"2026-07-24T00:23:20Z","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/2607.20531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aidar Shumbalov, Anna Kalyuzhnaya, Artem Kuznetsov, Ilya Galyukshev, Jerzy Kami\\'nski, Kirill Redko, Sergey Chuprin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T12:25:57Z","title":"DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20531","kind":"arxiv","version":1},"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":"sha256:392ffc32c06ceb9b99bdcf6cfbce7317aa057d6cb73e197d8173876bb5a9dfa7","target":"record","created_at":"2026-07-24T00:23:20Z","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":"80104e4593040c2942c821392571d05b437fca62b66736aa23c2bfddcbab5064","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T12:25:57Z","title_canon_sha256":"eb9720f77b7408a0ccf062584f89e92076ce49a290de63eba317790b2c6a4e98"},"schema_version":"1.0","source":{"id":"2607.20531","kind":"arxiv","version":1}},"canonical_sha256":"a7b092e873f70acc4bb1dc6e0a0fc28d73535426cc3d6c6830700a349ae3e3e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7b092e873f70acc4bb1dc6e0a0fc28d73535426cc3d6c6830700a349ae3e3e2","first_computed_at":"2026-07-24T00:23:20.659059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:20.659059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IyqBnouwJu+v4Yy/xYLz7ccin19b40pgC70kYBXniCSI2FG0Rex6345ar9/iEVLVz0kOOscl5dvsXzx+eUK8DA==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:20.659944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:392ffc32c06ceb9b99bdcf6cfbce7317aa057d6cb73e197d8173876bb5a9dfa7","sha256:0a478be51b140bd756ab2dd287d61b4abf1d44f297d05f328ce4d67458c4ddd1"],"state_sha256":"14b53b2586afc07b799f1fb634f946ff40fef5000a44fc60a22b322f81cdf989"}