{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SMBNTNYC2P6LKNHSYWF6GHYMFF","short_pith_number":"pith:SMBNTNYC","schema_version":"1.0","canonical_sha256":"9302d9b702d3fcb534f2c58be31f0c294f86c097413448a91db69e7ed8437c58","source":{"kind":"arxiv","id":"2305.14938","version":2},"attestation_state":"computed","paper":{"title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Shu, David Jurgens, Jiaxin Pei, Minje Choi, Sagar Kumar","submitted_at":"2023-05-24T09:21:06Z","abstract_excerpt":"Large language models (LLMs) have been shown to perform well at a variety of syntactic, discourse, and reasoning tasks. While LLMs are increasingly deployed in many forms including conversational agents that interact with humans, we lack a grounded benchmark to measure how well LLMs understand \\textit{social} language. Here, we introduce a new theory-driven benchmark, SocKET, that contains 58 NLP tasks testing social knowledge which we group into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness. In tests on the benchmark, we demonstrate that current mod"},"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":"2305.14938","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T09:21:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d8327e6d0c2862a9aaa25ddd0b18b6a769cacf2ed95fb4ec95e642e3e49354d","abstract_canon_sha256":"6d8cd3e395ab9dedfa84f80c95a5cdaf65ae9a9a01b4c64dced1a2ebe3df9059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:43.761706Z","signature_b64":"6DT0kMKwmGioz084e/ohbubDZtZ7WexZdFv/LHzIheUzLdLiDj5OImzfbTITf5o/DHeJIPWtGjVkNrN1cbLhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9302d9b702d3fcb534f2c58be31f0c294f86c097413448a91db69e7ed8437c58","last_reissued_at":"2026-07-05T08:02:43.761195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:43.761195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Shu, David Jurgens, Jiaxin Pei, Minje Choi, Sagar Kumar","submitted_at":"2023-05-24T09:21:06Z","abstract_excerpt":"Large language models (LLMs) have been shown to perform well at a variety of syntactic, discourse, and reasoning tasks. While LLMs are increasingly deployed in many forms including conversational agents that interact with humans, we lack a grounded benchmark to measure how well LLMs understand \\textit{social} language. Here, we introduce a new theory-driven benchmark, SocKET, that contains 58 NLP tasks testing social knowledge which we group into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness. In tests on the benchmark, we demonstrate that current mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14938","kind":"arxiv","version":2},"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/2305.14938/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":"2305.14938","created_at":"2026-07-05T08:02:43.761251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14938v2","created_at":"2026-07-05T08:02:43.761251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14938","created_at":"2026-07-05T08:02:43.761251+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMBNTNYC2P6L","created_at":"2026-07-05T08:02:43.761251+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMBNTNYC2P6LKNHS","created_at":"2026-07-05T08:02:43.761251+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMBNTNYC","created_at":"2026-07-05T08:02:43.761251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24536","citing_title":"Generating Place-Based Compromises Between Two Points of View","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF","json":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF.json","graph_json":"https://pith.science/api/pith-number/SMBNTNYC2P6LKNHSYWF6GHYMFF/graph.json","events_json":"https://pith.science/api/pith-number/SMBNTNYC2P6LKNHSYWF6GHYMFF/events.json","paper":"https://pith.science/paper/SMBNTNYC"},"agent_actions":{"view_html":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF","download_json":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF.json","view_paper":"https://pith.science/paper/SMBNTNYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14938&json=true","fetch_graph":"https://pith.science/api/pith-number/SMBNTNYC2P6LKNHSYWF6GHYMFF/graph.json","fetch_events":"https://pith.science/api/pith-number/SMBNTNYC2P6LKNHSYWF6GHYMFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF/action/storage_attestation","attest_author":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF/action/author_attestation","sign_citation":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF/action/citation_signature","submit_replication":"https://pith.science/pith/SMBNTNYC2P6LKNHSYWF6GHYMFF/action/replication_record"}},"created_at":"2026-07-05T08:02:43.761251+00:00","updated_at":"2026-07-05T08:02:43.761251+00:00"}