{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XARNTTBB6YMJLHGCNFBBCNAWBJ","short_pith_number":"pith:XARNTTBB","schema_version":"1.0","canonical_sha256":"b822d9cc21f618959cc269421134160a56374e8477d2d282ef5dc02d37ede14e","source":{"kind":"arxiv","id":"2506.11604","version":2},"attestation_state":"computed","paper":{"title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ren\\'e Peinl, Vincent Tischler","submitted_at":"2025-06-13T09:20:41Z","abstract_excerpt":"This paper introduces a novel benchmark dataset designed to evaluate the capabilities of Vision Language Models (VLMs) on tasks that combine visual reasoning with subject-specific background knowledge in the German language. In contrast to widely used English-language benchmarks that often rely on artificially difficult or decontextualized problems, this dataset draws from real middle school curricula across nine domains including mathematics, history, biology, and religion. The benchmark includes over 2,000 open-ended questions grounded in 486 images, ensuring that models must integrate visua"},"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":"2506.11604","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T09:20:41Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"6e1d131b3d450ba1d86da0df5b57000e305d1e639b1c9e7891f4d3ef7436b8a6","abstract_canon_sha256":"dcefb5f08aa038707390697ccaaae0e1856ec5df2c9d2898ff159c9f2c6e0d37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:17.296797Z","signature_b64":"wUis1kUYSX9AI60cIYG7bEDP/5/6oFIk/YSSYdvutt+kU4B6+tIKRvCU/ZVMtgfNAE6oQHjhHbIGweBBccEcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b822d9cc21f618959cc269421134160a56374e8477d2d282ef5dc02d37ede14e","last_reissued_at":"2026-07-05T11:28:17.296300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:17.296300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ren\\'e Peinl, Vincent Tischler","submitted_at":"2025-06-13T09:20:41Z","abstract_excerpt":"This paper introduces a novel benchmark dataset designed to evaluate the capabilities of Vision Language Models (VLMs) on tasks that combine visual reasoning with subject-specific background knowledge in the German language. In contrast to widely used English-language benchmarks that often rely on artificially difficult or decontextualized problems, this dataset draws from real middle school curricula across nine domains including mathematics, history, biology, and religion. The benchmark includes over 2,000 open-ended questions grounded in 486 images, ensuring that models must integrate visua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11604","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/2506.11604/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":"2506.11604","created_at":"2026-07-05T11:28:17.296367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11604v2","created_at":"2026-07-05T11:28:17.296367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11604","created_at":"2026-07-05T11:28:17.296367+00:00"},{"alias_kind":"pith_short_12","alias_value":"XARNTTBB6YMJ","created_at":"2026-07-05T11:28:17.296367+00:00"},{"alias_kind":"pith_short_16","alias_value":"XARNTTBB6YMJLHGC","created_at":"2026-07-05T11:28:17.296367+00:00"},{"alias_kind":"pith_short_8","alias_value":"XARNTTBB","created_at":"2026-07-05T11:28:17.296367+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/XARNTTBB6YMJLHGCNFBBCNAWBJ","json":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ.json","graph_json":"https://pith.science/api/pith-number/XARNTTBB6YMJLHGCNFBBCNAWBJ/graph.json","events_json":"https://pith.science/api/pith-number/XARNTTBB6YMJLHGCNFBBCNAWBJ/events.json","paper":"https://pith.science/paper/XARNTTBB"},"agent_actions":{"view_html":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ","download_json":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ.json","view_paper":"https://pith.science/paper/XARNTTBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11604&json=true","fetch_graph":"https://pith.science/api/pith-number/XARNTTBB6YMJLHGCNFBBCNAWBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XARNTTBB6YMJLHGCNFBBCNAWBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ/action/storage_attestation","attest_author":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ/action/author_attestation","sign_citation":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ/action/citation_signature","submit_replication":"https://pith.science/pith/XARNTTBB6YMJLHGCNFBBCNAWBJ/action/replication_record"}},"created_at":"2026-07-05T11:28:17.296367+00:00","updated_at":"2026-07-05T11:28:17.296367+00:00"}