{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QK5ZUHEAYLZ7SOFACNJVEIZSEP","short_pith_number":"pith:QK5ZUHEA","canonical_record":{"source":{"id":"2502.12895","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:32:17Z","cross_cats_sorted":[],"title_canon_sha256":"dd224f6b85da5295131a9d8c9dcd53ce24a62b48d9129e9b7bca3226f717fc86","abstract_canon_sha256":"425ae85bda213ccca62a2f17f60d0d104c2b2ca319be2958c151040838dba476"},"schema_version":"1.0"},"canonical_sha256":"82bb9a1c80c2f3f938a0135352233223eb01e86adcf49940c45ea016f7409412","source":{"kind":"arxiv","id":"2502.12895","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12895","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12895v2","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12895","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"QK5ZUHEAYLZ7","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"QK5ZUHEAYLZ7SOFA","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"QK5ZUHEA","created_at":"2026-07-05T10:43:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QK5ZUHEAYLZ7SOFACNJVEIZSEP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12895","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:32:17Z","cross_cats_sorted":[],"title_canon_sha256":"dd224f6b85da5295131a9d8c9dcd53ce24a62b48d9129e9b7bca3226f717fc86","abstract_canon_sha256":"425ae85bda213ccca62a2f17f60d0d104c2b2ca319be2958c151040838dba476"},"schema_version":"1.0"},"canonical_sha256":"82bb9a1c80c2f3f938a0135352233223eb01e86adcf49940c45ea016f7409412","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:26.435293Z","signature_b64":"adD1rAyfS4CktSipW8T8c3G1aKQsUvi9E2N4juucZwD18OvW6VNhNDODHU/GCmcjddpoL9SP7cakXV/rf6wWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82bb9a1c80c2f3f938a0135352233223eb01e86adcf49940c45ea016f7409412","last_reissued_at":"2026-07-05T10:43:26.434859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:26.434859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12895","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2uJ3Gtj0fQZ5xm+JY9URVGfg/l9z7bvcXhgUycju+bnXmgBF9nQPbLRqgdN3u71ExguytswDb6TOQdYVyonAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:21:13.140012Z"},"content_sha256":"66ccc39b14c76cc93ba4a0f55e0a45072e17bc4ecac6571d4193505be2b0290a","schema_version":"1.0","event_id":"sha256:66ccc39b14c76cc93ba4a0f55e0a45072e17bc4ecac6571d4193505be2b0290a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QK5ZUHEAYLZ7SOFACNJVEIZSEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual European Language Models: Benchmarking Approaches and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio Barth, Georg Rehm","submitted_at":"2025-02-18T14:32:17Z","abstract_excerpt":"The breakthrough of generative large language models (LLMs) that can solve different tasks through chat interaction has led to a significant increase in the use of general benchmarks to assess the quality or performance of these models beyond individual applications. There is also a need for better methods to evaluate and also to compare models due to the ever increasing number of new models published. However, most of the established benchmarks revolve around the English language. This paper analyses the benefits and limitations of current evaluation datasets, focusing on multilingual Europea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12895","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/2502.12895/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpqwhfHBec+QunQ208+VFTOUabCCGsYCyjkEBXk8YkrDBWMq7yr5rENz8570NYby0eER7ax/UMEcZmU1hGufCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:21:13.140760Z"},"content_sha256":"671e25920f6b929d53dc3bfa2c1f519323e13c7611d25fbbefe6e6adfdf8ca43","schema_version":"1.0","event_id":"sha256:671e25920f6b929d53dc3bfa2c1f519323e13c7611d25fbbefe6e6adfdf8ca43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/bundle.json","state_url":"https://pith.science/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T18:21:13Z","links":{"resolver":"https://pith.science/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP","bundle":"https://pith.science/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/bundle.json","state":"https://pith.science/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QK5ZUHEAYLZ7SOFACNJVEIZSEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QK5ZUHEAYLZ7SOFACNJVEIZSEP","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":"425ae85bda213ccca62a2f17f60d0d104c2b2ca319be2958c151040838dba476","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:32:17Z","title_canon_sha256":"dd224f6b85da5295131a9d8c9dcd53ce24a62b48d9129e9b7bca3226f717fc86"},"schema_version":"1.0","source":{"id":"2502.12895","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12895","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12895v2","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12895","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"QK5ZUHEAYLZ7","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"QK5ZUHEAYLZ7SOFA","created_at":"2026-07-05T10:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"QK5ZUHEA","created_at":"2026-07-05T10:43:26Z"}],"graph_snapshots":[{"event_id":"sha256:671e25920f6b929d53dc3bfa2c1f519323e13c7611d25fbbefe6e6adfdf8ca43","target":"graph","created_at":"2026-07-05T10:43:26Z","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/2502.12895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The breakthrough of generative large language models (LLMs) that can solve different tasks through chat interaction has led to a significant increase in the use of general benchmarks to assess the quality or performance of these models beyond individual applications. There is also a need for better methods to evaluate and also to compare models due to the ever increasing number of new models published. However, most of the established benchmarks revolve around the English language. This paper analyses the benefits and limitations of current evaluation datasets, focusing on multilingual Europea","authors_text":"Fabio Barth, Georg Rehm","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:32:17Z","title":"Multilingual European Language Models: Benchmarking Approaches and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12895","kind":"arxiv","version":2},"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":"sha256:66ccc39b14c76cc93ba4a0f55e0a45072e17bc4ecac6571d4193505be2b0290a","target":"record","created_at":"2026-07-05T10:43:26Z","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":"425ae85bda213ccca62a2f17f60d0d104c2b2ca319be2958c151040838dba476","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:32:17Z","title_canon_sha256":"dd224f6b85da5295131a9d8c9dcd53ce24a62b48d9129e9b7bca3226f717fc86"},"schema_version":"1.0","source":{"id":"2502.12895","kind":"arxiv","version":2}},"canonical_sha256":"82bb9a1c80c2f3f938a0135352233223eb01e86adcf49940c45ea016f7409412","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82bb9a1c80c2f3f938a0135352233223eb01e86adcf49940c45ea016f7409412","first_computed_at":"2026-07-05T10:43:26.434859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:26.434859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"adD1rAyfS4CktSipW8T8c3G1aKQsUvi9E2N4juucZwD18OvW6VNhNDODHU/GCmcjddpoL9SP7cakXV/rf6wWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:26.435293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12895","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66ccc39b14c76cc93ba4a0f55e0a45072e17bc4ecac6571d4193505be2b0290a","sha256:671e25920f6b929d53dc3bfa2c1f519323e13c7611d25fbbefe6e6adfdf8ca43"],"state_sha256":"bcb4d04de262f48a645af31bd947cf2faa1a8f3f3b3f21711f579888670f2ed3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CnZm86RtEwpiSMHREjD2ga9qFBaTBkWFozET5IyZHWZVTFd6nRQlNJIuvNhE0XduLLfoH8BKWs92rhA7UrHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:21:13.146203Z","bundle_sha256":"9c14b2ff5c8e7aff81a2197d33f365c5883ec7dc67cd175c9829e880f72eea92"}}