{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3FN33HFS4WIKSYLFZ55SCR5M6","short_pith_number":"pith:P3FN33HF","schema_version":"1.0","canonical_sha256":"7ecaddece5972c854b0b2e7bd90a3d67af4c271d15d47662cf162bb92b64d2cf","source":{"kind":"arxiv","id":"2606.01879","version":1},"attestation_state":"computed","paper":{"title":"CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Bing Qin, Jialong Tang, Xiachong Feng, Xiaocheng Feng, Xiayu Cao, Yangfan Ye, Zihan Zhang","submitted_at":"2026-06-01T08:25:12Z","abstract_excerpt":"Existing research largely reduces cultural intelligence in LLMs to a knowledge-level problem, overlooking whether models can effectively utilize their acquired knowledge in realistic scenarios. To bridge this gap, we introduce CultureForest, a benchmark for \\textit{Cultural Norm Grounded Reasoning}. Each question is grounded in a small set of atomic norms, enabling verifiable and attributable evaluation. CultureForest comprises 5,378 examples across 8 domains and 53 countries/regions, and supports a progressive evaluation from multiple-choice to open-ended generation. Extensive experiments rev"},"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":"2606.01879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T08:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"fe799f4c4ce7ec48f2f988caf2fafbee0a4fd3a89442a2bce61b95c7ecaacb37","abstract_canon_sha256":"064f51a22d194dcfa608f11cce95f7f2dddbc132ac99fbd0cf152c0297954fd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:59.403513Z","signature_b64":"rv62++AUQa2FqoODk2La/11uT4hUstsjPUL47GQpa/ZXVBXCJOslDyywbeW8f3KxdseqK3ouV+zkICFK0pV7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ecaddece5972c854b0b2e7bd90a3d67af4c271d15d47662cf162bb92b64d2cf","last_reissued_at":"2026-06-02T02:04:59.403024Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:59.403024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Bing Qin, Jialong Tang, Xiachong Feng, Xiaocheng Feng, Xiayu Cao, Yangfan Ye, Zihan Zhang","submitted_at":"2026-06-01T08:25:12Z","abstract_excerpt":"Existing research largely reduces cultural intelligence in LLMs to a knowledge-level problem, overlooking whether models can effectively utilize their acquired knowledge in realistic scenarios. To bridge this gap, we introduce CultureForest, a benchmark for \\textit{Cultural Norm Grounded Reasoning}. Each question is grounded in a small set of atomic norms, enabling verifiable and attributable evaluation. CultureForest comprises 5,378 examples across 8 domains and 53 countries/regions, and supports a progressive evaluation from multiple-choice to open-ended generation. Extensive experiments rev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01879","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/2606.01879/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":"2606.01879","created_at":"2026-06-02T02:04:59.403084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01879v1","created_at":"2026-06-02T02:04:59.403084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01879","created_at":"2026-06-02T02:04:59.403084+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3FN33HFS4WI","created_at":"2026-06-02T02:04:59.403084+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3FN33HFS4WIKSYL","created_at":"2026-06-02T02:04:59.403084+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3FN33HF","created_at":"2026-06-02T02:04:59.403084+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/P3FN33HFS4WIKSYLFZ55SCR5M6","json":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6.json","graph_json":"https://pith.science/api/pith-number/P3FN33HFS4WIKSYLFZ55SCR5M6/graph.json","events_json":"https://pith.science/api/pith-number/P3FN33HFS4WIKSYLFZ55SCR5M6/events.json","paper":"https://pith.science/paper/P3FN33HF"},"agent_actions":{"view_html":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6","download_json":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6.json","view_paper":"https://pith.science/paper/P3FN33HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01879&json=true","fetch_graph":"https://pith.science/api/pith-number/P3FN33HFS4WIKSYLFZ55SCR5M6/graph.json","fetch_events":"https://pith.science/api/pith-number/P3FN33HFS4WIKSYLFZ55SCR5M6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6/action/storage_attestation","attest_author":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6/action/author_attestation","sign_citation":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6/action/citation_signature","submit_replication":"https://pith.science/pith/P3FN33HFS4WIKSYLFZ55SCR5M6/action/replication_record"}},"created_at":"2026-06-02T02:04:59.403084+00:00","updated_at":"2026-06-02T02:04:59.403084+00:00"}