{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XBA6ZIWV7O4BXHJGSOA6OFBUYV","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":"50a0ce4c31b6dfa36a18db2379ee3337e1ea341dc39699a6f52e6cfad098546b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T12:04:28Z","title_canon_sha256":"257fa2fb6224fa83cb4917bdc5d14f8299539b5a36d7729e139edee767d3767c"},"schema_version":"1.0","source":{"id":"2403.19346","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19346","created_at":"2026-07-05T11:13:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19346v6","created_at":"2026-07-05T11:13:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19346","created_at":"2026-07-05T11:13:08Z"},{"alias_kind":"pith_short_12","alias_value":"XBA6ZIWV7O4B","created_at":"2026-07-05T11:13:08Z"},{"alias_kind":"pith_short_16","alias_value":"XBA6ZIWV7O4BXHJG","created_at":"2026-07-05T11:13:08Z"},{"alias_kind":"pith_short_8","alias_value":"XBA6ZIWV","created_at":"2026-07-05T11:13:08Z"}],"graph_snapshots":[{"event_id":"sha256:ed4286c39032583c14b730d1cd2cdd7bff53ce5f301e95f1c6875581a806130a","target":"graph","created_at":"2026-07-05T11:13:08Z","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/2403.19346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues, models frequently proceed as if the problem is well-posed, producing incorrect answers or falling into overthinking and verbose self-correction. To systematically investigate this overlooked vulnerability, we propose the \\textbf{Unreasonable Math Problems (UMP)} benchmark, designed to evaluate LLMs' ability to detect and respond to unreasonable math problem state","authors_text":"Bin Wang, Damai Dai, Jingyuan Ma, Lei Sha, Qun Liu, Rui Li, Weilin Luo, Zhifang Sui, Zihang Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T12:04:28Z","title":"Large Language Models Struggle with Unreasonability in Math Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19346","kind":"arxiv","version":6},"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:a4e5e055e67dd9e7333d1bf4e214bb56029119491f2d9090c17b63a5692873f6","target":"record","created_at":"2026-07-05T11:13:08Z","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":"50a0ce4c31b6dfa36a18db2379ee3337e1ea341dc39699a6f52e6cfad098546b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T12:04:28Z","title_canon_sha256":"257fa2fb6224fa83cb4917bdc5d14f8299539b5a36d7729e139edee767d3767c"},"schema_version":"1.0","source":{"id":"2403.19346","kind":"arxiv","version":6}},"canonical_sha256":"b841eca2d5fbb81b9d269381e71434c541641b62f5d03c619bb2538913052674","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b841eca2d5fbb81b9d269381e71434c541641b62f5d03c619bb2538913052674","first_computed_at":"2026-07-05T11:13:08.522786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:08.522786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2kxJOTxd/diB+XLlZgBgwa/L0Q815dhaIkkp2UZ5EtptETUPHPmb/jsLQYq1RYjs2Rc6lo4avnW2c6Gouj42Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:08.523339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19346","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4e5e055e67dd9e7333d1bf4e214bb56029119491f2d9090c17b63a5692873f6","sha256:ed4286c39032583c14b730d1cd2cdd7bff53ce5f301e95f1c6875581a806130a"],"state_sha256":"e431fe258fc7831599275ce6bc1a1c40b22acd9ddfb442d04c41e2e52658afdb"}