{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7RD3FUEIBFCPEETWBFKVQ25GLJ","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":"0c318db2d079dcaa5fb0da4ecb81a707b729c3daa017ecdba0e5237319b376cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-11T21:53:20Z","title_canon_sha256":"000d66c0ae973ef30aa58af8497715aab2ea17221ad41aaa9eed3d29aeaebdaa"},"schema_version":"1.0","source":{"id":"2409.07641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07641","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07641v1","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07641","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"7RD3FUEIBFCP","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"7RD3FUEIBFCPEETW","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"7RD3FUEI","created_at":"2026-07-05T09:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:bdeb10749a7b3092792b2dd80b864c5e110929f302516872894a2b6bd19cf150","target":"graph","created_at":"2026-07-05T09:06:12Z","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/2409.07641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SimulBench, a benchmark designed to evaluate large language models (LLMs) across a diverse collection of creative simulation scenarios, such as acting as a Linux terminal or playing text games with users. While these simulation tasks serve as effective measures of an LLM's general intelligence, they are seldom incorporated into existing benchmarks. A major challenge is to develop an evaluation framework for testing different LLMs fairly while preserving the multi-round interactive nature of simulation tasks between users and AI. To tackle this issue, we suggest using a fixed LLM a","authors_text":"Bill Yuchen Lin, Jie Huang, Qi Jia, Tianyu Zheng, Xiang Yue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-11T21:53:20Z","title":"SimulBench: Evaluating Language Models with Creative Simulation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07641","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:e3466beab6fe7b1df197ae5cdbd36864e4ed96d6c3634d3465de4c3b8358b659","target":"record","created_at":"2026-07-05T09:06:12Z","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":"0c318db2d079dcaa5fb0da4ecb81a707b729c3daa017ecdba0e5237319b376cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-11T21:53:20Z","title_canon_sha256":"000d66c0ae973ef30aa58af8497715aab2ea17221ad41aaa9eed3d29aeaebdaa"},"schema_version":"1.0","source":{"id":"2409.07641","kind":"arxiv","version":1}},"canonical_sha256":"fc47b2d0880944f212760955586ba65a52ed6bcc3669020b546c8c9a9e84a19e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc47b2d0880944f212760955586ba65a52ed6bcc3669020b546c8c9a9e84a19e","first_computed_at":"2026-07-05T09:06:12.898929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:12.898929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1fi4zekug/yS0Tz0tjOXIzRmTJ4EyWKFHVW3JgkBSPB+wB2PCjs5reOtWTDfCtd+x65f1kFYBvxHXS8Ibwf3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:12.899355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3466beab6fe7b1df197ae5cdbd36864e4ed96d6c3634d3465de4c3b8358b659","sha256:bdeb10749a7b3092792b2dd80b864c5e110929f302516872894a2b6bd19cf150"],"state_sha256":"17f8174c82cbc4dafff0f2bc52ebd3103d58f6541a21bef0b0f3f5e1de38b1b0"}