{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7JOPH3S4Z56T2YBL6TUX7CB3SZ","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":"da894c5d885b7f8856aef44ea512b51a11101aebe9c254255d404ce6d5548f5e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T13:16:41Z","title_canon_sha256":"6df64cdd07cb4fae766e785b955150f6d90a895799b8364a976926167243faf3"},"schema_version":"1.0","source":{"id":"2408.15778","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15778","created_at":"2026-07-05T09:19:31Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15778v4","created_at":"2026-07-05T09:19:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15778","created_at":"2026-07-05T09:19:31Z"},{"alias_kind":"pith_short_12","alias_value":"7JOPH3S4Z56T","created_at":"2026-07-05T09:19:31Z"},{"alias_kind":"pith_short_16","alias_value":"7JOPH3S4Z56T2YBL","created_at":"2026-07-05T09:19:31Z"},{"alias_kind":"pith_short_8","alias_value":"7JOPH3S4","created_at":"2026-07-05T09:19:31Z"}],"graph_snapshots":[{"event_id":"sha256:6b5d107191346171bf4afc84938207db163133437a6aac42698579d18e82354b","target":"graph","created_at":"2026-07-05T09:19:31Z","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/2408.15778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated notable capabilities across various tasks, showcasing complex problem-solving abilities. Understanding and executing complex rules, along with multi-step planning, are fundamental to logical reasoning and critical for practical LLM agents and decision-making systems. However, evaluating LLMs as effective rule-based executors and planners remains underexplored. In this paper, we introduce LogicGame, a novel benchmark designed to evaluate the comprehensive rule understanding, execution, and planning capabilities of LLMs. Unlike traditional benchmark","authors_text":"Hongning Wang, Jiale Cheng, Jiayi Gui, Jie Tang, Minlie Huang, Xiao Liu, Xiaotao Gu, Yiming Liu, Yuxiao Dong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T13:16:41Z","title":"LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15778","kind":"arxiv","version":4},"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:ef0e34461448e6ac94d789fda71fdee9beba0aefbee908c46636640b8e3cabd8","target":"record","created_at":"2026-07-05T09:19:31Z","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":"da894c5d885b7f8856aef44ea512b51a11101aebe9c254255d404ce6d5548f5e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T13:16:41Z","title_canon_sha256":"6df64cdd07cb4fae766e785b955150f6d90a895799b8364a976926167243faf3"},"schema_version":"1.0","source":{"id":"2408.15778","kind":"arxiv","version":4}},"canonical_sha256":"fa5cf3ee5ccf7d3d602bf4e97f883b9677f65e60fd7af17777a94aadc5e27589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa5cf3ee5ccf7d3d602bf4e97f883b9677f65e60fd7af17777a94aadc5e27589","first_computed_at":"2026-07-05T09:19:31.035136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:31.035136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMcYtSSJJhJ7GvRFhA61FbOHH4oBpH5fr0GcIFCpBRjjyReCM696IuQMP/wojapv6UpAg6IIYqTNo1+bjUzrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:31.035582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15778","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef0e34461448e6ac94d789fda71fdee9beba0aefbee908c46636640b8e3cabd8","sha256:6b5d107191346171bf4afc84938207db163133437a6aac42698579d18e82354b"],"state_sha256":"beefc4ca712115849a976bab4114a17ed9080d18f4b0b722ba969ce2cdc2c684"}