{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YXECJJ7JWID7HFEK5R3H24GDEK","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":"e7809d9b97facbe0edc4944947690bb8cab8a975b5f6fc06f5e3ab86a30478de","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T23:41:22Z","title_canon_sha256":"55fdf0dfb540685990684c55c0ca7b55e6edb175822c52ccadd5b528bfabd1e5"},"schema_version":"1.0","source":{"id":"2501.11790","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11790","created_at":"2026-06-24T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11790v5","created_at":"2026-06-24T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11790","created_at":"2026-06-24T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"YXECJJ7JWID7","created_at":"2026-06-24T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"YXECJJ7JWID7HFEK","created_at":"2026-06-24T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"YXECJJ7J","created_at":"2026-06-24T01:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:83073e600eb16f33b144f9b4f2850ec1dac4f83128ab47c762856e95d1f1c72d","target":"graph","created_at":"2026-06-24T01:14:56Z","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/2501.11790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we build question-generating functions to produce random variable q","authors_text":"Feiran Huang, Hao Wu, Hongxia Yang, Junnan Dong, Linyi Li, Su Dong, Xiao Huang, Yilin Xiao, Yujing Zhang, Zhu Wang, Zijin Hong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T23:41:22Z","title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11790","kind":"arxiv","version":5},"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":"sha256:7f5a5904633f7c52f3e3c890647810f1f6d826f1efd7a66e5c41543c6a499ef4","target":"record","created_at":"2026-06-24T01:14:56Z","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":"e7809d9b97facbe0edc4944947690bb8cab8a975b5f6fc06f5e3ab86a30478de","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T23:41:22Z","title_canon_sha256":"55fdf0dfb540685990684c55c0ca7b55e6edb175822c52ccadd5b528bfabd1e5"},"schema_version":"1.0","source":{"id":"2501.11790","kind":"arxiv","version":5}},"canonical_sha256":"c5c824a7e9b207f3948aec767d70c32299f955301878c80cb905f188f4ed828f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5c824a7e9b207f3948aec767d70c32299f955301878c80cb905f188f4ed828f","first_computed_at":"2026-06-24T01:14:56.372116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:56.372116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Nq4d8iqLbmRwlOvbFscCjraPeBYc5NWHKSQNoh0YuffKtFFvpI9lop4IhD8q5su+15d/vdsRvz/kfwNDAaWAA==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:56.372592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11790","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f5a5904633f7c52f3e3c890647810f1f6d826f1efd7a66e5c41543c6a499ef4","sha256:83073e600eb16f33b144f9b4f2850ec1dac4f83128ab47c762856e95d1f1c72d"],"state_sha256":"63f5c1d90fcd5cfaed32a453fadfefde83d8d2e9686438951977bf7a7efb86b3"}