{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MGNCGSXZAFYALVLVOW4NQENBEN","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":"1427bda511abc7c5a839fc34577bde2bc8817566b329c4c3bbab3808fb1ccae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:17:47Z","title_canon_sha256":"5ee152779658eeac8008353b43cdf101588be2d049f6bf1ed697089672b2418a"},"schema_version":"1.0","source":{"id":"2504.18373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18373","created_at":"2026-07-05T10:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18373v1","created_at":"2026-07-05T10:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18373","created_at":"2026-07-05T10:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"MGNCGSXZAFYA","created_at":"2026-07-05T10:54:06Z"},{"alias_kind":"pith_short_16","alias_value":"MGNCGSXZAFYALVLV","created_at":"2026-07-05T10:54:06Z"},{"alias_kind":"pith_short_8","alias_value":"MGNCGSXZ","created_at":"2026-07-05T10:54:06Z"}],"graph_snapshots":[{"event_id":"sha256:1fdc3e0dbc6a8fc340f3ba121400d984b728b27a2e3fdd22e0b47162ef23fbe2","target":"graph","created_at":"2026-07-05T10:54:06Z","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/2504.18373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, multi-agent frameworks powered by large language models (LLMs) have advanced rapidly. Despite this progress, there is still a notable absence of benchmark datasets specifically tailored to evaluate their performance. To bridge this gap, we introduce Auto-SLURP, a benchmark dataset aimed at evaluating LLM-based multi-agent frameworks in the context of intelligent personal assistants. Auto-SLURP extends the original SLURP dataset -- initially developed for natural language understanding tasks -- by relabeling the data and integrating simulated servers and external services. This","authors_text":"Lei Shen, Xiaoyu Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:17:47Z","title":"Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18373","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":"sha256:53b9f0ba366807fa745471e42ec859f53eb81a53c9f6e4e27c441ca67f91cca6","target":"record","created_at":"2026-07-05T10:54:06Z","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":"1427bda511abc7c5a839fc34577bde2bc8817566b329c4c3bbab3808fb1ccae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:17:47Z","title_canon_sha256":"5ee152779658eeac8008353b43cdf101588be2d049f6bf1ed697089672b2418a"},"schema_version":"1.0","source":{"id":"2504.18373","kind":"arxiv","version":1}},"canonical_sha256":"619a234af9017005d57575b8d811a12348094d25cbb8f3f574c0af956eddf8ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"619a234af9017005d57575b8d811a12348094d25cbb8f3f574c0af956eddf8ae","first_computed_at":"2026-07-05T10:54:06.111404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:06.111404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RqKTS4hGpYUAO18X39WCE//bpuZR9U65tMrd+k+q1ak6lOoJYeURSKf9bpD8hpL51jfY7y4sliDhLqpTl7cVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:06.111884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53b9f0ba366807fa745471e42ec859f53eb81a53c9f6e4e27c441ca67f91cca6","sha256:1fdc3e0dbc6a8fc340f3ba121400d984b728b27a2e3fdd22e0b47162ef23fbe2"],"state_sha256":"578c6a05b1ad72d3e279f4f0a7f5b31f6d9fe3584064cbf25e4ad9bb50e0e652"}