{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4K4AVYWJB5W77X4KZEI6D36QPV","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":"ddca690f7e106c934485a73d9b880dbd2d4089f000e8aa1ae9c621a4229e053f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T17:35:44Z","title_canon_sha256":"9b6022367dbc429b7ccfdb32464f40b22e35d780fc25c3150abe744021cfc6a6"},"schema_version":"1.0","source":{"id":"2410.23252","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23252","created_at":"2026-07-05T10:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23252v3","created_at":"2026-07-05T10:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23252","created_at":"2026-07-05T10:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"4K4AVYWJB5W7","created_at":"2026-07-05T10:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"4K4AVYWJB5W77X4K","created_at":"2026-07-05T10:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"4K4AVYWJ","created_at":"2026-07-05T10:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:257035be26992c50f5ab8d2d231ace853e6e642743c532448bc98686052d9576","target":"graph","created_at":"2026-07-05T10:27:18Z","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/2410.23252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) expand into performing as agents for real-world applications beyond traditional NLP tasks, evaluating their robustness becomes increasingly important. However, existing benchmarks often overlook critical dimensions like cultural and social awareness. To address these, we introduce CASA, a benchmark designed to assess LLM agents' sensitivity to cultural and social norms across two web-based tasks: online shopping and social discussion forums. Our approach evaluates LLM agents' ability to detect and appropriately respond to norm-violating user queries and observat","authors_text":"Alexander R. Fabbri, Chien-Sheng Wu, Divyansh Agarwal, Haoyi Qiu, Kung-Hsiang Huang, Nanyun Peng, Sarah Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T17:35:44Z","title":"Evaluating Cultural and Social Awareness of LLM Web Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23252","kind":"arxiv","version":3},"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":"sha256:8bba3c6c9c7f10a2d6d02ac0a2e7ce9496eba4f4f42dbcc98b55e4f8c87a663f","target":"record","created_at":"2026-07-05T10:27:18Z","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":"ddca690f7e106c934485a73d9b880dbd2d4089f000e8aa1ae9c621a4229e053f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T17:35:44Z","title_canon_sha256":"9b6022367dbc429b7ccfdb32464f40b22e35d780fc25c3150abe744021cfc6a6"},"schema_version":"1.0","source":{"id":"2410.23252","kind":"arxiv","version":3}},"canonical_sha256":"e2b80ae2c90f6dffdf8ac911e1efd07d6b7aeb00e6e3e32b5fd6dae5274d2258","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2b80ae2c90f6dffdf8ac911e1efd07d6b7aeb00e6e3e32b5fd6dae5274d2258","first_computed_at":"2026-07-05T10:27:18.667788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:18.667788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nkIIx1vwAEH26Yi09/fS+QWgHg3NBrIMxU7JPRqtJk2SFkyqFNFeslmHZQCGCLliNlCIA3RZX8wlrY85hZDPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:18.668474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23252","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bba3c6c9c7f10a2d6d02ac0a2e7ce9496eba4f4f42dbcc98b55e4f8c87a663f","sha256:257035be26992c50f5ab8d2d231ace853e6e642743c532448bc98686052d9576"],"state_sha256":"632e2dd2d3e7192ff6355c90925ce41785d4a47547038b06c38ca72cad333576"}