{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QGUIOKH3KBEKHSXHKHDXXYXOOB","short_pith_number":"pith:QGUIOKH3","schema_version":"1.0","canonical_sha256":"81a88728fb5048a3cae751c77be2ee704acb655d8428a39b522d8a87053b2aab","source":{"kind":"arxiv","id":"2608.01395","version":1},"attestation_state":"computed","paper":{"title":"Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"A. Altar L\\\"user, David Schlangen, Eszter Bukovszky, Jelle Psurek, Karl Osswald, Sherzod Hakimov","submitted_at":"2026-08-02T17:20:01Z","abstract_excerpt":"We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are language-agnostic it extends to a new language by localising a fixed set of prompt and word-list files. Evaluating nine open-weight and commercial LLMs, we find that no open-weight model covers the EU-24 well: in every official language both commercial systems outscore"},"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":"2608.01395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T17:20:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b51cfd04c6a0831543c3125161a57e6608240b46e88e0e22eaa5fb19c9a710d","abstract_canon_sha256":"135bc395ccc03240ab8b0f8897d131218f43ea13b9b6b4d475bdfef78e5b1e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:56.953495Z","signature_b64":"YdT7SkAD3qIimJymwu21/ODSuJ2S7X3LFutk8YNHjXF0Oza8CtKVzSn4clIttxJrn0ixs37IjZZwGVn5Vb4nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a88728fb5048a3cae751c77be2ee704acb655d8428a39b522d8a87053b2aab","last_reissued_at":"2026-08-04T02:04:56.951979Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:56.951979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"A. Altar L\\\"user, David Schlangen, Eszter Bukovszky, Jelle Psurek, Karl Osswald, Sherzod Hakimov","submitted_at":"2026-08-02T17:20:01Z","abstract_excerpt":"We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are language-agnostic it extends to a new language by localising a fixed set of prompt and word-list files. Evaluating nine open-weight and commercial LLMs, we find that no open-weight model covers the EU-24 well: in every official language both commercial systems outscore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01395","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/2608.01395/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":"2608.01395","created_at":"2026-08-04T02:04:56.953406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01395v1","created_at":"2026-08-04T02:04:56.953406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01395","created_at":"2026-08-04T02:04:56.953406+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGUIOKH3KBEK","created_at":"2026-08-04T02:04:56.953406+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGUIOKH3KBEKHSXH","created_at":"2026-08-04T02:04:56.953406+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGUIOKH3","created_at":"2026-08-04T02:04:56.953406+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/QGUIOKH3KBEKHSXHKHDXXYXOOB","json":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB.json","graph_json":"https://pith.science/api/pith-number/QGUIOKH3KBEKHSXHKHDXXYXOOB/graph.json","events_json":"https://pith.science/api/pith-number/QGUIOKH3KBEKHSXHKHDXXYXOOB/events.json","paper":"https://pith.science/paper/QGUIOKH3"},"agent_actions":{"view_html":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB","download_json":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB.json","view_paper":"https://pith.science/paper/QGUIOKH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01395&json=true","fetch_graph":"https://pith.science/api/pith-number/QGUIOKH3KBEKHSXHKHDXXYXOOB/graph.json","fetch_events":"https://pith.science/api/pith-number/QGUIOKH3KBEKHSXHKHDXXYXOOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB/action/storage_attestation","attest_author":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB/action/author_attestation","sign_citation":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB/action/citation_signature","submit_replication":"https://pith.science/pith/QGUIOKH3KBEKHSXHKHDXXYXOOB/action/replication_record"}},"created_at":"2026-08-04T02:04:56.953406+00:00","updated_at":"2026-08-04T02:04:56.953406+00:00"}