{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ERIKW5NULSALI755C3PSGKZLWH","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":"f7076233fa76c0efa749232d30a8f0778eb357d17fe321248582a4d703a2181a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T03:59:28Z","title_canon_sha256":"7faacf8b82f0305d56dff5477166d62da1e2d896e09bdb2cba727e1c6bb9d3f0"},"schema_version":"1.0","source":{"id":"2308.04026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04026","created_at":"2026-07-05T06:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04026v1","created_at":"2026-07-05T06:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04026","created_at":"2026-07-05T06:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"ERIKW5NULSAL","created_at":"2026-07-05T06:39:21Z"},{"alias_kind":"pith_short_16","alias_value":"ERIKW5NULSALI755","created_at":"2026-07-05T06:39:21Z"},{"alias_kind":"pith_short_8","alias_value":"ERIKW5NU","created_at":"2026-07-05T06:39:21Z"}],"graph_snapshots":[{"event_id":"sha256:c380a3df3eb2cfd753a5e6fa2b9a59316601ca4db02b79095290d5d228c3f237","target":"graph","created_at":"2026-07-05T06:39:21Z","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/2308.04026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question. Existing evaluation methods suffer from following shortcomings: (1) constrained evaluation abilities, (2) vulnerable benchmarks, (3) unobjective metrics. We suggest that task-based evaluation, where LLM agents complete tasks in a simulated environment, is a one-for-all solution to solve above problems. We present AgentSims, an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in. Researchers can bui","authors_text":"Aochi Zhang, Haoran Zhao, Huqiuyue Ping, Jiaju Lin, Qin Chen, Yiting Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T03:59:28Z","title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04026","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":"sha256:70acb45aadbd00d43c1df3df14f7c37775dc16ac9f4b495dde2e5fe73293382e","target":"record","created_at":"2026-07-05T06:39:21Z","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":"f7076233fa76c0efa749232d30a8f0778eb357d17fe321248582a4d703a2181a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T03:59:28Z","title_canon_sha256":"7faacf8b82f0305d56dff5477166d62da1e2d896e09bdb2cba727e1c6bb9d3f0"},"schema_version":"1.0","source":{"id":"2308.04026","kind":"arxiv","version":1}},"canonical_sha256":"2450ab75b45c80b47fbd16df232b2bb1e0d6268eebcbc765369a9b81d81dcaf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2450ab75b45c80b47fbd16df232b2bb1e0d6268eebcbc765369a9b81d81dcaf3","first_computed_at":"2026-07-05T06:39:21.220225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:21.220225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IfLGyrVvhX/d+VK+r6AD4hLYZRx4gzx4cmG12TbOn7V5KtRIWqpaMfziYiU2BCVaIrZX6fy6GIeNektio0z0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:21.220730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70acb45aadbd00d43c1df3df14f7c37775dc16ac9f4b495dde2e5fe73293382e","sha256:c380a3df3eb2cfd753a5e6fa2b9a59316601ca4db02b79095290d5d228c3f237"],"state_sha256":"3191d5838fc635364914a173d20aeeba848e6662432b192289ca24b4c7c3b87c"}