{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ECAHBYNJHSOZPLX7ZJXTGQNOOH","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":"063fdefe54dea39a41ff72ac3befe9802f8c2d69030e96d215331f05967666fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T17:59:05Z","title_canon_sha256":"be457e37c52370ec34ed4d7918f68e50d6dc3a1d7e8eaf699c38633cf2ee376e"},"schema_version":"1.0","source":{"id":"2608.09925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09925","created_at":"2026-08-11T02:25:28Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09925v1","created_at":"2026-08-11T02:25:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09925","created_at":"2026-08-11T02:25:28Z"},{"alias_kind":"pith_short_12","alias_value":"ECAHBYNJHSOZ","created_at":"2026-08-11T02:25:28Z"},{"alias_kind":"pith_short_16","alias_value":"ECAHBYNJHSOZPLX7","created_at":"2026-08-11T02:25:28Z"},{"alias_kind":"pith_short_8","alias_value":"ECAHBYNJ","created_at":"2026-08-11T02:25:28Z"}],"graph_snapshots":[{"event_id":"sha256:2d72b46a8a82d47cba7307a552e3d37d74eda769e2ec505ddcfc4afb05b057d1","target":"graph","created_at":"2026-08-11T02:25:28Z","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/2608.09925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly being deployed in governmental settings, yet few existing evaluation frameworks jointly reflect the values of public administration and the linguistic requirements of non-English contexts. We present the \"Grip on LLMs\" framework, a systematic evaluation suite for Dutch governmental use developed in collaboration with domain experts from a major Dutch municipal organisation. Through an advisory board process, user research, and a survey of the users of a civil-servant chatbot, we identify six evaluation dimensions (factuality, honesty, social bias, energy ","authors_text":"Gossa L\\^o, Iva Gornishka, Laurens Samson, Sennay Ghebreab, Yuki M. Asano","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T17:59:05Z","title":"From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09925","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:ba12dcbffe69e91e8706a536c100014751f411f3ea21f6bac62c687523b6534e","target":"record","created_at":"2026-08-11T02:25:28Z","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":"063fdefe54dea39a41ff72ac3befe9802f8c2d69030e96d215331f05967666fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T17:59:05Z","title_canon_sha256":"be457e37c52370ec34ed4d7918f68e50d6dc3a1d7e8eaf699c38633cf2ee376e"},"schema_version":"1.0","source":{"id":"2608.09925","kind":"arxiv","version":1}},"canonical_sha256":"208070e1a93c9d97aeffca6f3341ae71d2cccdd24a081fdb0094d19b77550576","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"208070e1a93c9d97aeffca6f3341ae71d2cccdd24a081fdb0094d19b77550576","first_computed_at":"2026-08-11T02:25:28.401767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:25:28.401767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+8HbGxfvdSJrbE4c7lDGzRqBcxVLurgLLzRvMP3b4Y1vjUmTieXCdkDaVam2PGecwaXS1E/soQM/bDIYOjFeAA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:25:28.403258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba12dcbffe69e91e8706a536c100014751f411f3ea21f6bac62c687523b6534e","sha256:2d72b46a8a82d47cba7307a552e3d37d74eda769e2ec505ddcfc4afb05b057d1"],"state_sha256":"e39ddae58daaf4589ca12a56130fc2ba2a55f14391540f886d932075fb33fa56"}