{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFLLYBSXVM4Y76L52GMYQVJA56","short_pith_number":"pith:MFLLYBSX","schema_version":"1.0","canonical_sha256":"6156bc0657ab398ff97dd199885520ef9d2d3bc568560426f966fc3535c13fd7","source":{"kind":"arxiv","id":"2607.23440","version":1},"attestation_state":"computed","paper":{"title":"Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongtian Shao, Hai Hu, Kejia Zhang, Siyuan Song, Tianjian Zhu, Xiaojing Zhao","submitted_at":"2026-07-26T03:39:29Z","abstract_excerpt":"In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accuracy ($\\Delta_{acc}$) between existing but low-frequency xiehouyu and novel ones as an index for memorization. $\\Delta_{acc}$ for native speakers is very low, suggesting similar processing mechanisms. H"},"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":"2607.23440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T03:39:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"361bbed896fa6e5f08094f904689718da730e806cd3ea196ea74c638e9b96b75","abstract_canon_sha256":"4ef7bd8f9a01d97b12b508414ec8daf1304aca4da8e59786f0497985406f9373"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:52.976874Z","signature_b64":"jifn6hifRTOdhjaO4McDqSuHqoXY9q4Mbxsnjf+j7N840bpimdW92+pEfjhLemO+6/2hYsvgymoFoz0YpiEBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6156bc0657ab398ff97dd199885520ef9d2d3bc568560426f966fc3535c13fd7","last_reissued_at":"2026-07-28T01:22:52.976102Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:52.976102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongtian Shao, Hai Hu, Kejia Zhang, Siyuan Song, Tianjian Zhu, Xiaojing Zhao","submitted_at":"2026-07-26T03:39:29Z","abstract_excerpt":"In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accuracy ($\\Delta_{acc}$) between existing but low-frequency xiehouyu and novel ones as an index for memorization. $\\Delta_{acc}$ for native speakers is very low, suggesting similar processing mechanisms. H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23440","kind":"arxiv","version":1},"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/2607.23440/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":"2607.23440","created_at":"2026-07-28T01:22:52.976495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23440v1","created_at":"2026-07-28T01:22:52.976495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23440","created_at":"2026-07-28T01:22:52.976495+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFLLYBSXVM4Y","created_at":"2026-07-28T01:22:52.976495+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFLLYBSXVM4Y76L5","created_at":"2026-07-28T01:22:52.976495+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFLLYBSX","created_at":"2026-07-28T01:22:52.976495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56","json":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56.json","graph_json":"https://pith.science/api/pith-number/MFLLYBSXVM4Y76L52GMYQVJA56/graph.json","events_json":"https://pith.science/api/pith-number/MFLLYBSXVM4Y76L52GMYQVJA56/events.json","paper":"https://pith.science/paper/MFLLYBSX"},"agent_actions":{"view_html":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56","download_json":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56.json","view_paper":"https://pith.science/paper/MFLLYBSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23440&json=true","fetch_graph":"https://pith.science/api/pith-number/MFLLYBSXVM4Y76L52GMYQVJA56/graph.json","fetch_events":"https://pith.science/api/pith-number/MFLLYBSXVM4Y76L52GMYQVJA56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56/action/storage_attestation","attest_author":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56/action/author_attestation","sign_citation":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56/action/citation_signature","submit_replication":"https://pith.science/pith/MFLLYBSXVM4Y76L52GMYQVJA56/action/replication_record"}},"created_at":"2026-07-28T01:22:52.976495+00:00","updated_at":"2026-07-28T01:22:52.976495+00:00"}