{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M4ELZCL5YCHUQ44DSMVKZPQNLY","short_pith_number":"pith:M4ELZCL5","schema_version":"1.0","canonical_sha256":"6708bc897dc08f487383932aacbe0d5e09ded61fc20446ed304c0521a146fd1a","source":{"kind":"arxiv","id":"2404.02491","version":4},"attestation_state":"computed","paper":{"title":"Measuring Social Norms of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Jianhao Shen, Kexin Tang, Ming Zhang, Ye Yuan","submitted_at":"2024-04-03T05:58:57Z","abstract_excerpt":"We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of social norms to solve. Our dataset features the largest set of social norm skills, consisting of 402 skills and 12,383 questions covering a wide set of social norms ranging from opinions and arguments to culture and laws. We design our dataset according to the K-12 curriculum. This enables the direct comparison of the social understanding of large language models to humans, more specifically, elementary students. Whil"},"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":"2404.02491","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T05:58:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"36e8d2c51fe702188ee1a404cd2fc38c4a2060c1245044c42e6381119997b5c8","abstract_canon_sha256":"7e3d0b3dcd1fe2b5625a226379bf9e0462901b1fe493f73db81869ec1112a2cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:52.246322Z","signature_b64":"8xkKLW3+ZUAySAhTtBY+5cN1nLJh4RHzLUOnXN/NjmD2XZxqc+Cwt0AGzwysSgLzRj1sGFJrQrOUad7/IniYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6708bc897dc08f487383932aacbe0d5e09ded61fc20446ed304c0521a146fd1a","last_reissued_at":"2026-07-05T08:21:52.245822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:52.245822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Social Norms of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Jianhao Shen, Kexin Tang, Ming Zhang, Ye Yuan","submitted_at":"2024-04-03T05:58:57Z","abstract_excerpt":"We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of social norms to solve. Our dataset features the largest set of social norm skills, consisting of 402 skills and 12,383 questions covering a wide set of social norms ranging from opinions and arguments to culture and laws. We design our dataset according to the K-12 curriculum. This enables the direct comparison of the social understanding of large language models to humans, more specifically, elementary students. Whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02491","kind":"arxiv","version":4},"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/2404.02491/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":"2404.02491","created_at":"2026-07-05T08:21:52.245883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02491v4","created_at":"2026-07-05T08:21:52.245883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02491","created_at":"2026-07-05T08:21:52.245883+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4ELZCL5YCHU","created_at":"2026-07-05T08:21:52.245883+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4ELZCL5YCHUQ44D","created_at":"2026-07-05T08:21:52.245883+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4ELZCL5","created_at":"2026-07-05T08:21:52.245883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00088","citing_title":"How large language models judge and influence human cooperation","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY","json":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY.json","graph_json":"https://pith.science/api/pith-number/M4ELZCL5YCHUQ44DSMVKZPQNLY/graph.json","events_json":"https://pith.science/api/pith-number/M4ELZCL5YCHUQ44DSMVKZPQNLY/events.json","paper":"https://pith.science/paper/M4ELZCL5"},"agent_actions":{"view_html":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY","download_json":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY.json","view_paper":"https://pith.science/paper/M4ELZCL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02491&json=true","fetch_graph":"https://pith.science/api/pith-number/M4ELZCL5YCHUQ44DSMVKZPQNLY/graph.json","fetch_events":"https://pith.science/api/pith-number/M4ELZCL5YCHUQ44DSMVKZPQNLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY/action/storage_attestation","attest_author":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY/action/author_attestation","sign_citation":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY/action/citation_signature","submit_replication":"https://pith.science/pith/M4ELZCL5YCHUQ44DSMVKZPQNLY/action/replication_record"}},"created_at":"2026-07-05T08:21:52.245883+00:00","updated_at":"2026-07-05T08:21:52.245883+00:00"}