{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECAHBYNJHSOZPLX7ZJXTGQNOOH","short_pith_number":"pith:ECAHBYNJ","schema_version":"1.0","canonical_sha256":"208070e1a93c9d97aeffca6f3341ae71d2cccdd24a081fdb0094d19b77550576","source":{"kind":"arxiv","id":"2608.09925","version":1},"attestation_state":"computed","paper":{"title":"From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gossa L\\^o, Iva Gornishka, Laurens Samson, Sennay Ghebreab, Yuki M. Asano","submitted_at":"2026-08-10T17:59:05Z","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 "},"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":"2608.09925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T17:59:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be457e37c52370ec34ed4d7918f68e50d6dc3a1d7e8eaf699c38633cf2ee376e","abstract_canon_sha256":"063fdefe54dea39a41ff72ac3befe9802f8c2d69030e96d215331f05967666fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:25:28.403258Z","signature_b64":"+8HbGxfvdSJrbE4c7lDGzRqBcxVLurgLLzRvMP3b4Y1vjUmTieXCdkDaVam2PGecwaXS1E/soQM/bDIYOjFeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208070e1a93c9d97aeffca6f3341ae71d2cccdd24a081fdb0094d19b77550576","last_reissued_at":"2026-08-11T02:25:28.401767Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:25:28.401767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gossa L\\^o, Iva Gornishka, Laurens Samson, Sennay Ghebreab, Yuki M. Asano","submitted_at":"2026-08-10T17:59:05Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09925","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/2608.09925/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":"2608.09925","created_at":"2026-08-11T02:25:28.402387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09925v1","created_at":"2026-08-11T02:25:28.402387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09925","created_at":"2026-08-11T02:25:28.402387+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECAHBYNJHSOZ","created_at":"2026-08-11T02:25:28.402387+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECAHBYNJHSOZPLX7","created_at":"2026-08-11T02:25:28.402387+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECAHBYNJ","created_at":"2026-08-11T02:25:28.402387+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/ECAHBYNJHSOZPLX7ZJXTGQNOOH","json":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH.json","graph_json":"https://pith.science/api/pith-number/ECAHBYNJHSOZPLX7ZJXTGQNOOH/graph.json","events_json":"https://pith.science/api/pith-number/ECAHBYNJHSOZPLX7ZJXTGQNOOH/events.json","paper":"https://pith.science/paper/ECAHBYNJ"},"agent_actions":{"view_html":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH","download_json":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH.json","view_paper":"https://pith.science/paper/ECAHBYNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09925&json=true","fetch_graph":"https://pith.science/api/pith-number/ECAHBYNJHSOZPLX7ZJXTGQNOOH/graph.json","fetch_events":"https://pith.science/api/pith-number/ECAHBYNJHSOZPLX7ZJXTGQNOOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH/action/storage_attestation","attest_author":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH/action/author_attestation","sign_citation":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH/action/citation_signature","submit_replication":"https://pith.science/pith/ECAHBYNJHSOZPLX7ZJXTGQNOOH/action/replication_record"}},"created_at":"2026-08-11T02:25:28.402387+00:00","updated_at":"2026-08-11T02:25:28.402387+00:00"}