{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HLB2X3PKVVGDP7UPQ7ZHLGG3YX","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":"bd2296bab2036bc0f28c70a1fc63c2eb01ae7b1c643e13846ce0e8edee3afa3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-04-01T10:06:04Z","title_canon_sha256":"cef29276c4de3b5473a52358d2cd892658d8dce874c08d9dde52de73ca36c751"},"schema_version":"1.0","source":{"id":"2404.01023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01023","created_at":"2026-06-08T01:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01023v1","created_at":"2026-06-08T01:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01023","created_at":"2026-06-08T01:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"HLB2X3PKVVGD","created_at":"2026-06-08T01:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"HLB2X3PKVVGDP7UP","created_at":"2026-06-08T01:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"HLB2X3PK","created_at":"2026-06-08T01:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:998c3600fb05581827403fd1b3ab18a089e362635f556001c99ab955db4fd8e3","target":"graph","created_at":"2026-06-08T01:03:41Z","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/2404.01023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) have become integral to both research and daily operations, rigorous evaluation is crucial. This assessment is important not only for individual tasks but also for understanding their societal impact and potential risks. Despite extensive efforts to examine LLMs from various perspectives, there is a noticeable lack of multi-agent AI models specifically designed to evaluate the performance of different LLMs. To address this gap, we introduce a novel multi-agent AI model that aims to assess and compare the performance of various LLMs. Our model consists of eight d","authors_text":"Kari Syst\\\"a, Muhammad Waseem, Pekka Abrahamsson, Zeeshan Rasheed","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-04-01T10:06:04Z","title":"Large Language Model Evaluation Via Multi AI Agents: Preliminary results"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01023","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:c92d2b466c656244dafed67bb5138e5c08318d175e34f743ace6ba03b032f1c0","target":"record","created_at":"2026-06-08T01:03:41Z","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":"bd2296bab2036bc0f28c70a1fc63c2eb01ae7b1c643e13846ce0e8edee3afa3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-04-01T10:06:04Z","title_canon_sha256":"cef29276c4de3b5473a52358d2cd892658d8dce874c08d9dde52de73ca36c751"},"schema_version":"1.0","source":{"id":"2404.01023","kind":"arxiv","version":1}},"canonical_sha256":"3ac3abedeaad4c37fe8f87f27598dbc5d7f977f9d8af0138268492bf24318d01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ac3abedeaad4c37fe8f87f27598dbc5d7f977f9d8af0138268492bf24318d01","first_computed_at":"2026-06-08T01:03:41.337044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:41.337044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p1a4RYfyyei27JnZgGjiiirYP/MrvHbORsczEasmA0/K17AMY/Oe55d/QBDfmMANR7aTcLd1MFRT2McriaiIBg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:41.338247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c92d2b466c656244dafed67bb5138e5c08318d175e34f743ace6ba03b032f1c0","sha256:998c3600fb05581827403fd1b3ab18a089e362635f556001c99ab955db4fd8e3"],"state_sha256":"58230ca73bb628e589dd4469bf57cb46a06c7c0df287fa4d65b29cfc50ae8fd6"}