{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KNKV7FX47DW2DJAP5E7MBXGIJP","short_pith_number":"pith:KNKV7FX4","schema_version":"1.0","canonical_sha256":"53555f96fcf8eda1a40fe93ec0dcc84bd48e688b4f632b2768840b4b81a222d2","source":{"kind":"arxiv","id":"2504.21605","version":1},"attestation_state":"computed","paper":{"title":"RDF-Based Structured Quality Assessment Representation of Multilingual LLM Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andreas Both, Jonas Gwozdz","submitted_at":"2025-04-30T13:06:40Z","abstract_excerpt":"Large Language Models (LLMs) increasingly serve as knowledge interfaces, yet systematically assessing their reliability with conflicting information remains difficult. We propose an RDF-based framework to assess multilingual LLM quality, focusing on knowledge conflicts. Our approach captures model responses across four distinct context conditions (complete, incomplete, conflicting, and no-context information) in German and English. This structured representation enables the comprehensive analysis of knowledge leakage-where models favor training data over provided context-error detection, and m"},"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":"2504.21605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:06:40Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"01348e233e36f81983c193e64a12c9f0dbe29945da10c20b3dce38fff5fa4059","abstract_canon_sha256":"835a1b37d781b20b303a48968a4711cb77540f792167cbf2bded7a36c9f8973e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:26.784212Z","signature_b64":"H/gtyu0R2TQZtLyCZ9f7s1jHU/lQFJ6SEkTRfzACZRtkdyF0BU8d6gk8AUJAY64hS3/n8BYUHiDE3oDDJioKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53555f96fcf8eda1a40fe93ec0dcc84bd48e688b4f632b2768840b4b81a222d2","last_reissued_at":"2026-07-05T10:56:26.783748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:26.783748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RDF-Based Structured Quality Assessment Representation of Multilingual LLM Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andreas Both, Jonas Gwozdz","submitted_at":"2025-04-30T13:06:40Z","abstract_excerpt":"Large Language Models (LLMs) increasingly serve as knowledge interfaces, yet systematically assessing their reliability with conflicting information remains difficult. We propose an RDF-based framework to assess multilingual LLM quality, focusing on knowledge conflicts. Our approach captures model responses across four distinct context conditions (complete, incomplete, conflicting, and no-context information) in German and English. This structured representation enables the comprehensive analysis of knowledge leakage-where models favor training data over provided context-error detection, and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21605","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/2504.21605/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":"2504.21605","created_at":"2026-07-05T10:56:26.783804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21605v1","created_at":"2026-07-05T10:56:26.783804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21605","created_at":"2026-07-05T10:56:26.783804+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNKV7FX47DW2","created_at":"2026-07-05T10:56:26.783804+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNKV7FX47DW2DJAP","created_at":"2026-07-05T10:56:26.783804+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNKV7FX4","created_at":"2026-07-05T10:56:26.783804+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/KNKV7FX47DW2DJAP5E7MBXGIJP","json":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP.json","graph_json":"https://pith.science/api/pith-number/KNKV7FX47DW2DJAP5E7MBXGIJP/graph.json","events_json":"https://pith.science/api/pith-number/KNKV7FX47DW2DJAP5E7MBXGIJP/events.json","paper":"https://pith.science/paper/KNKV7FX4"},"agent_actions":{"view_html":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP","download_json":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP.json","view_paper":"https://pith.science/paper/KNKV7FX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21605&json=true","fetch_graph":"https://pith.science/api/pith-number/KNKV7FX47DW2DJAP5E7MBXGIJP/graph.json","fetch_events":"https://pith.science/api/pith-number/KNKV7FX47DW2DJAP5E7MBXGIJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP/action/storage_attestation","attest_author":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP/action/author_attestation","sign_citation":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP/action/citation_signature","submit_replication":"https://pith.science/pith/KNKV7FX47DW2DJAP5E7MBXGIJP/action/replication_record"}},"created_at":"2026-07-05T10:56:26.783804+00:00","updated_at":"2026-07-05T10:56:26.783804+00:00"}