{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7OXBYWU2FFR4AMJ444AN7E3KWE","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":"d6f4ac63430d0ff016ec7ef364cc728602764cd3417043690ed4ea1998d61f38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T21:46:27Z","title_canon_sha256":"b89dbd94f5e8fb9100185c37324bf62f381c79ea1e6db431ed6778ce68226930"},"schema_version":"1.0","source":{"id":"2311.08562","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08562","created_at":"2026-07-05T09:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08562v3","created_at":"2026-07-05T09:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08562","created_at":"2026-07-05T09:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"7OXBYWU2FFR4","created_at":"2026-07-05T09:40:54Z"},{"alias_kind":"pith_short_16","alias_value":"7OXBYWU2FFR4AMJ4","created_at":"2026-07-05T09:40:54Z"},{"alias_kind":"pith_short_8","alias_value":"7OXBYWU2","created_at":"2026-07-05T09:40:54Z"}],"graph_snapshots":[{"event_id":"sha256:86695c602fe051d1884db4a4eb6c062cee8995604471daf9c282f02e1fafdb2d","target":"graph","created_at":"2026-07-05T09:40:54Z","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/2311.08562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating exceptional reasoning, tool usage, and memory capabilities. As their applications expand into multi-agent environments, there arises a need for a comprehensive evaluation framework that captures LLMs' reasoning, planning, collaboration, and other social abilities. This work introduces a novel competition-based benchmark framework specifically designed to assess LLMs within multi-agent settings, providing quantitative metrics to evaluate their judgment, reasoning, deception, self-awareness, coope","authors_text":"Daquan Zhou, Hongyu Ren, Jiashi Feng, Kurt Keutzer, Lin Xu, See Kiong Ng, Zhen Dong, Zhiyuan Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T21:46:27Z","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08562","kind":"arxiv","version":3},"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":"sha256:2b09496c4ac57f48c5b0fd7ddb2f40f6aea083450bb45a315101b6375a7d1e5b","target":"record","created_at":"2026-07-05T09:40:54Z","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":"d6f4ac63430d0ff016ec7ef364cc728602764cd3417043690ed4ea1998d61f38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T21:46:27Z","title_canon_sha256":"b89dbd94f5e8fb9100185c37324bf62f381c79ea1e6db431ed6778ce68226930"},"schema_version":"1.0","source":{"id":"2311.08562","kind":"arxiv","version":3}},"canonical_sha256":"fbae1c5a9a2963c0313ce700df936ab1244f4e32e6b146cf8ecb6dc7728f8695","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbae1c5a9a2963c0313ce700df936ab1244f4e32e6b146cf8ecb6dc7728f8695","first_computed_at":"2026-07-05T09:40:54.026591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:54.026591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dpRW7iGwUIuwAFyhuhELrg2VPtgK+s/GmF683TEiD5CK/gcsjIA3OJOMWk9RmPQyS+E69nhflh1xGVMmOs+2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:54.027184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08562","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b09496c4ac57f48c5b0fd7ddb2f40f6aea083450bb45a315101b6375a7d1e5b","sha256:86695c602fe051d1884db4a4eb6c062cee8995604471daf9c282f02e1fafdb2d"],"state_sha256":"0a1ab410ede66e9c6c542df07995da6a9ed212707a7edc9849abc37214218aa1"}