{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SEKQ6UADHPBHOSN2Q4FA2FW6O5","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":"c25b8a30706f27105d4a408306a7205dd812e5fc21535654d57a3c2ed9ce20c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T09:06:34Z","title_canon_sha256":"ad1bead2485eba193f60d0bc91fc941a834e28d9411a0fe138d0fe4cb6b4b216"},"schema_version":"1.0","source":{"id":"2403.03558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03558","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03558v1","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03558","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"SEKQ6UADHPBH","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"SEKQ6UADHPBHOSN2","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"SEKQ6UAD","created_at":"2026-07-05T07:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:87fe330f487e3f0a5f7006e9a3bdd7c116b4cf1843bb78a5e0b5dd1248b7fd8e","target":"graph","created_at":"2026-07-05T07:52:49Z","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/2403.03558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical ex","authors_text":"Hui Zhao, Jiawen Wu, Qipeng Guo, Xipeng Qiu, Yuhong Sun, Zhangyue Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T09:06:34Z","title":"Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03558","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":"sha256:93dcdd8945c19ace6143268485969987c4a82b0a13e68312f80a6d8a38fe91ae","target":"record","created_at":"2026-07-05T07:52:49Z","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":"c25b8a30706f27105d4a408306a7205dd812e5fc21535654d57a3c2ed9ce20c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T09:06:34Z","title_canon_sha256":"ad1bead2485eba193f60d0bc91fc941a834e28d9411a0fe138d0fe4cb6b4b216"},"schema_version":"1.0","source":{"id":"2403.03558","kind":"arxiv","version":1}},"canonical_sha256":"91150f50033bc27749ba870a0d16de775f7ddeaf436a4758e985dd2e2953464f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91150f50033bc27749ba870a0d16de775f7ddeaf436a4758e985dd2e2953464f","first_computed_at":"2026-07-05T07:52:49.983705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:49.983705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OU7ONDilHIDfouURI+OH8p7jCWuIbtrMxfP5WlZD5qCovo46PquSimJURs4eVNlm2Gdto51JXaTQOoZddBI3AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:49.984057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93dcdd8945c19ace6143268485969987c4a82b0a13e68312f80a6d8a38fe91ae","sha256:87fe330f487e3f0a5f7006e9a3bdd7c116b4cf1843bb78a5e0b5dd1248b7fd8e"],"state_sha256":"0bdc66bafe42c600944b6563fb2aad04aeaa3ce5f14866d38bf89c52b0bb0a2c"}