{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YXECJJ7JWID7HFEK5R3H24GDEK","short_pith_number":"pith:YXECJJ7J","schema_version":"1.0","canonical_sha256":"c5c824a7e9b207f3948aec767d70c32299f955301878c80cb905f188f4ed828f","source":{"kind":"arxiv","id":"2501.11790","version":5},"attestation_state":"computed","paper":{"title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feiran Huang, Hao Wu, Hongxia Yang, Junnan Dong, Linyi Li, Su Dong, Xiao Huang, Yilin Xiao, Yujing Zhang, Zhu Wang, Zijin Hong","submitted_at":"2025-01-20T23:41:22Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.11790","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T23:41:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55fdf0dfb540685990684c55c0ca7b55e6edb175822c52ccadd5b528bfabd1e5","abstract_canon_sha256":"e7809d9b97facbe0edc4944947690bb8cab8a975b5f6fc06f5e3ab86a30478de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:56.372592Z","signature_b64":"+Nq4d8iqLbmRwlOvbFscCjraPeBYc5NWHKSQNoh0YuffKtFFvpI9lop4IhD8q5su+15d/vdsRvz/kfwNDAaWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5c824a7e9b207f3948aec767d70c32299f955301878c80cb905f188f4ed828f","last_reissued_at":"2026-06-24T01:14:56.372116Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:56.372116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feiran Huang, Hao Wu, Hongxia Yang, Junnan Dong, Linyi Li, Su Dong, Xiao Huang, Yilin Xiao, Yujing Zhang, Zhu Wang, Zijin Hong","submitted_at":"2025-01-20T23:41:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11790","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.11790/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.11790","created_at":"2026-06-24T01:14:56.372176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11790v5","created_at":"2026-06-24T01:14:56.372176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11790","created_at":"2026-06-24T01:14:56.372176+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXECJJ7JWID7","created_at":"2026-06-24T01:14:56.372176+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXECJJ7JWID7HFEK","created_at":"2026-06-24T01:14:56.372176+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXECJJ7J","created_at":"2026-06-24T01:14:56.372176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK","json":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK.json","graph_json":"https://pith.science/api/pith-number/YXECJJ7JWID7HFEK5R3H24GDEK/graph.json","events_json":"https://pith.science/api/pith-number/YXECJJ7JWID7HFEK5R3H24GDEK/events.json","paper":"https://pith.science/paper/YXECJJ7J"},"agent_actions":{"view_html":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK","download_json":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK.json","view_paper":"https://pith.science/paper/YXECJJ7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11790&json=true","fetch_graph":"https://pith.science/api/pith-number/YXECJJ7JWID7HFEK5R3H24GDEK/graph.json","fetch_events":"https://pith.science/api/pith-number/YXECJJ7JWID7HFEK5R3H24GDEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK/action/storage_attestation","attest_author":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK/action/author_attestation","sign_citation":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK/action/citation_signature","submit_replication":"https://pith.science/pith/YXECJJ7JWID7HFEK5R3H24GDEK/action/replication_record"}},"created_at":"2026-06-24T01:14:56.372176+00:00","updated_at":"2026-06-24T01:14:56.372176+00:00"}