{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CZ2YMCLKIK76IGTFLPYFLWXUL5","short_pith_number":"pith:CZ2YMCLK","schema_version":"1.0","canonical_sha256":"167586096a42bfe41a655bf055daf45f52ca000baac738547521a3a55093511d","source":{"kind":"arxiv","id":"2502.13766","version":1},"attestation_state":"computed","paper":{"title":"GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Lauscher, Carolin Holtermann, Chris Biemann, Florian Schneider","submitted_at":"2025-02-19T14:27:40Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently gained attention due to their distinctive performance and broad applicability. While it has been previously shown that their efficacy in usage scenarios involving non-Western contexts falls short, existing studies are limited in scope, covering just a narrow range of cultures, focusing exclusively on a small number of cultural aspects, or evaluating a limited selection of models on a single task only. Towards globally inclusive LVLM research, we introduce GIMMICK, an extensive multimodal benchmark designed to assess a broad spectrum of cultura"},"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":"2502.13766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:27:40Z","cross_cats_sorted":[],"title_canon_sha256":"10279fc6da6edb300354e05f1bc5fa1f4790d0c89703e622acffdbd993a7aa26","abstract_canon_sha256":"b044b11257dc5f976c3b39461e53a0fbc2feef8889165c020c75412618300f96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:00.352136Z","signature_b64":"XH2VBK2C546chmX/b3SpH6qroQay1Ss5PA97cgAztNo6tFFxsY4p6ZNTU5mYmw1uGASZiOQJ3NFTqnlRo+49Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167586096a42bfe41a655bf055daf45f52ca000baac738547521a3a55093511d","last_reissued_at":"2026-07-05T10:17:00.351165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:00.351165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Lauscher, Carolin Holtermann, Chris Biemann, Florian Schneider","submitted_at":"2025-02-19T14:27:40Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently gained attention due to their distinctive performance and broad applicability. While it has been previously shown that their efficacy in usage scenarios involving non-Western contexts falls short, existing studies are limited in scope, covering just a narrow range of cultures, focusing exclusively on a small number of cultural aspects, or evaluating a limited selection of models on a single task only. Towards globally inclusive LVLM research, we introduce GIMMICK, an extensive multimodal benchmark designed to assess a broad spectrum of cultura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13766","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/2502.13766/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":"2502.13766","created_at":"2026-07-05T10:17:00.351564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13766v1","created_at":"2026-07-05T10:17:00.351564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13766","created_at":"2026-07-05T10:17:00.351564+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ2YMCLKIK76","created_at":"2026-07-05T10:17:00.351564+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ2YMCLKIK76IGTF","created_at":"2026-07-05T10:17:00.351564+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ2YMCLK","created_at":"2026-07-05T10:17:00.351564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22793","citing_title":"Evaluation of Cultural Competence of Vision-Language Models","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5","json":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5.json","graph_json":"https://pith.science/api/pith-number/CZ2YMCLKIK76IGTFLPYFLWXUL5/graph.json","events_json":"https://pith.science/api/pith-number/CZ2YMCLKIK76IGTFLPYFLWXUL5/events.json","paper":"https://pith.science/paper/CZ2YMCLK"},"agent_actions":{"view_html":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5","download_json":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5.json","view_paper":"https://pith.science/paper/CZ2YMCLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13766&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ2YMCLKIK76IGTFLPYFLWXUL5/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ2YMCLKIK76IGTFLPYFLWXUL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5/action/storage_attestation","attest_author":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5/action/author_attestation","sign_citation":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5/action/citation_signature","submit_replication":"https://pith.science/pith/CZ2YMCLKIK76IGTFLPYFLWXUL5/action/replication_record"}},"created_at":"2026-07-05T10:17:00.351564+00:00","updated_at":"2026-07-05T10:17:00.351564+00:00"}