{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KX5G57MEJL7OXWK7VVDCJSSXG6","short_pith_number":"pith:KX5G57ME","schema_version":"1.0","canonical_sha256":"55fa6efd844afeebd95fad4624ca57378f7ac7a7d2326fb3853125ac23a78d1c","source":{"kind":"arxiv","id":"2607.21445","version":1},"attestation_state":"computed","paper":{"title":"When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Mosolova, Djam\\'e Seddah","submitted_at":"2026-07-23T15:52:00Z","abstract_excerpt":"Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions"},"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":"2607.21445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T15:52:00Z","cross_cats_sorted":[],"title_canon_sha256":"3bf9948d998c5c6e5cb0575b9eb033266fa0f956832cfade2fbc5490a263d6e7","abstract_canon_sha256":"63ec0c24466d4609d98b448556a03f88034d9cd702e292923aa13fa99cad1e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:33.077407Z","signature_b64":"oLyRgyfYoOLqSzwpucpy7PhOZR9scqENisgYw6+bJWqsdS7Mr+A77lN8Tc399W5/lFTV34UaB7Hm55YMCa0QDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55fa6efd844afeebd95fad4624ca57378f7ac7a7d2326fb3853125ac23a78d1c","last_reissued_at":"2026-07-24T01:24:33.076490Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:33.076490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Mosolova, Djam\\'e Seddah","submitted_at":"2026-07-23T15:52:00Z","abstract_excerpt":"Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21445","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/2607.21445/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":"2607.21445","created_at":"2026-07-24T01:24:33.076954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21445v1","created_at":"2026-07-24T01:24:33.076954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21445","created_at":"2026-07-24T01:24:33.076954+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX5G57MEJL7O","created_at":"2026-07-24T01:24:33.076954+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX5G57MEJL7OXWK7","created_at":"2026-07-24T01:24:33.076954+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX5G57ME","created_at":"2026-07-24T01:24:33.076954+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/KX5G57MEJL7OXWK7VVDCJSSXG6","json":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6.json","graph_json":"https://pith.science/api/pith-number/KX5G57MEJL7OXWK7VVDCJSSXG6/graph.json","events_json":"https://pith.science/api/pith-number/KX5G57MEJL7OXWK7VVDCJSSXG6/events.json","paper":"https://pith.science/paper/KX5G57ME"},"agent_actions":{"view_html":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6","download_json":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6.json","view_paper":"https://pith.science/paper/KX5G57ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21445&json=true","fetch_graph":"https://pith.science/api/pith-number/KX5G57MEJL7OXWK7VVDCJSSXG6/graph.json","fetch_events":"https://pith.science/api/pith-number/KX5G57MEJL7OXWK7VVDCJSSXG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6/action/storage_attestation","attest_author":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6/action/author_attestation","sign_citation":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6/action/citation_signature","submit_replication":"https://pith.science/pith/KX5G57MEJL7OXWK7VVDCJSSXG6/action/replication_record"}},"created_at":"2026-07-24T01:24:33.076954+00:00","updated_at":"2026-07-24T01:24:33.076954+00:00"}