{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D3UIFHFHTJR6CI32IRPAUGIIII","short_pith_number":"pith:D3UIFHFH","schema_version":"1.0","canonical_sha256":"1ee8829ca79a63e1237a445e0a1908421d3100be334cb75a4bf801dc948391f1","source":{"kind":"arxiv","id":"2507.20700","version":1},"attestation_state":"computed","paper":{"title":"When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanna Shcharbakova, Josef van Genabith, Natalia Skachkova, Tatiana Anikina","submitted_at":"2025-07-28T10:49:04Z","abstract_excerpt":"The rapid spread of multilingual misinformation requires robust automated fact verification systems capable of handling fine-grained veracity assessments across diverse languages. While large language models have shown remarkable capabilities across many NLP tasks, their effectiveness for multilingual claim verification with nuanced classification schemes remains understudied. We conduct a comprehensive evaluation of five state-of-the-art language models on the X-Fact dataset, which spans 25 languages with seven distinct veracity categories. Our experiments compare small language models (encod"},"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":"2507.20700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T10:49:04Z","cross_cats_sorted":[],"title_canon_sha256":"1f392b0b79ccb269739a2aaf92ef035c328272df46f675c2d593c4656088fb68","abstract_canon_sha256":"1a657b9ce0e389c4147795a50f1ed0f3bdd40e75471bc984b721d3b8a7f8f3e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:24.404388Z","signature_b64":"GO/9k5x+4orA6JhHuZyKsFfNn16BRFvaw4f24bnuSpxpWOQzfo57VPeEjKK8NqBmOMMXwVtAMOXlfFrFjWPkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ee8829ca79a63e1237a445e0a1908421d3100be334cb75a4bf801dc948391f1","last_reissued_at":"2026-07-05T11:44:24.403848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:24.403848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanna Shcharbakova, Josef van Genabith, Natalia Skachkova, Tatiana Anikina","submitted_at":"2025-07-28T10:49:04Z","abstract_excerpt":"The rapid spread of multilingual misinformation requires robust automated fact verification systems capable of handling fine-grained veracity assessments across diverse languages. While large language models have shown remarkable capabilities across many NLP tasks, their effectiveness for multilingual claim verification with nuanced classification schemes remains understudied. We conduct a comprehensive evaluation of five state-of-the-art language models on the X-Fact dataset, which spans 25 languages with seven distinct veracity categories. Our experiments compare small language models (encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20700","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/2507.20700/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":"2507.20700","created_at":"2026-07-05T11:44:24.403913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20700v1","created_at":"2026-07-05T11:44:24.403913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20700","created_at":"2026-07-05T11:44:24.403913+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3UIFHFHTJR6","created_at":"2026-07-05T11:44:24.403913+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3UIFHFHTJR6CI32","created_at":"2026-07-05T11:44:24.403913+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3UIFHFH","created_at":"2026-07-05T11:44:24.403913+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/D3UIFHFHTJR6CI32IRPAUGIIII","json":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII.json","graph_json":"https://pith.science/api/pith-number/D3UIFHFHTJR6CI32IRPAUGIIII/graph.json","events_json":"https://pith.science/api/pith-number/D3UIFHFHTJR6CI32IRPAUGIIII/events.json","paper":"https://pith.science/paper/D3UIFHFH"},"agent_actions":{"view_html":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII","download_json":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII.json","view_paper":"https://pith.science/paper/D3UIFHFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20700&json=true","fetch_graph":"https://pith.science/api/pith-number/D3UIFHFHTJR6CI32IRPAUGIIII/graph.json","fetch_events":"https://pith.science/api/pith-number/D3UIFHFHTJR6CI32IRPAUGIIII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII/action/storage_attestation","attest_author":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII/action/author_attestation","sign_citation":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII/action/citation_signature","submit_replication":"https://pith.science/pith/D3UIFHFHTJR6CI32IRPAUGIIII/action/replication_record"}},"created_at":"2026-07-05T11:44:24.403913+00:00","updated_at":"2026-07-05T11:44:24.403913+00:00"}