{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZ36JD5LM2ZC6SVEJKGZOS5O5O","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":"130fe9b8045f1558b74f2c34cafcfbe738e8167cf93281c20096f602ad952782","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T13:20:08Z","title_canon_sha256":"c03296919f6efb53dd8a47aa21607eba250b7217ce03a0ae4b384b265f8f9a6d"},"schema_version":"1.0","source":{"id":"2406.17535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17535","created_at":"2026-07-05T08:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17535v1","created_at":"2026-07-05T08:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17535","created_at":"2026-07-05T08:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"PZ36JD5LM2ZC","created_at":"2026-07-05T08:36:36Z"},{"alias_kind":"pith_short_16","alias_value":"PZ36JD5LM2ZC6SVE","created_at":"2026-07-05T08:36:36Z"},{"alias_kind":"pith_short_8","alias_value":"PZ36JD5L","created_at":"2026-07-05T08:36:36Z"}],"graph_snapshots":[{"event_id":"sha256:16a9322f1e8274eba52b9c7920d75ee13ade2c72583bcdfa2ae652a3be0950b8","target":"graph","created_at":"2026-07-05T08:36:36Z","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/2406.17535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to generate and manipulate human language, highlighting their potential across various applications. Evaluating LLMs in languages other than English is crucial for ensuring their linguistic versatility, cultural relevance, and applicability in diverse global contexts, thus broadening their usability and effectiveness. We tackle this challenge by introducing a structured benchmark using the INVALSI tests, a set of well-established assessments designed to measure educational competencies across Italy. O","authors_text":"Andrea Seveso, Antonio Serino, Daniele Potert\\`i, Fabio Mercorio, Mario Mezzanzanica","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T13:20:08Z","title":"Disce aut Deficere: Evaluating LLMs Proficiency on the INVALSI Italian Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17535","kind":"arxiv","version":1},"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":"sha256:8e3a55956ed905e10c19999d99ce19110cba9c168d6639b5ed4361659fb5115c","target":"record","created_at":"2026-07-05T08:36:36Z","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":"130fe9b8045f1558b74f2c34cafcfbe738e8167cf93281c20096f602ad952782","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T13:20:08Z","title_canon_sha256":"c03296919f6efb53dd8a47aa21607eba250b7217ce03a0ae4b384b265f8f9a6d"},"schema_version":"1.0","source":{"id":"2406.17535","kind":"arxiv","version":1}},"canonical_sha256":"7e77e48fab66b22f4aa44a8d974baeeba268e42bd8796d4c9d197364fb016385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e77e48fab66b22f4aa44a8d974baeeba268e42bd8796d4c9d197364fb016385","first_computed_at":"2026-07-05T08:36:36.527519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:36.527519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i58J9NN0IdZfVEJc9tH+slp+d14pu3YRX+K1xzmNBuSeWOAqmzs88x1rdD+kUmm6RMZJxnqBFleEz0+50zPjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:36.528061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e3a55956ed905e10c19999d99ce19110cba9c168d6639b5ed4361659fb5115c","sha256:16a9322f1e8274eba52b9c7920d75ee13ade2c72583bcdfa2ae652a3be0950b8"],"state_sha256":"69feda17faca512fa771e13fe28454fc76b112d5a60a43f25673b0359ae61421"}