{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CVONFEY4QCHKC3RD4ZQ7ZERFS6","short_pith_number":"pith:CVONFEY4","schema_version":"1.0","canonical_sha256":"155cd2931c808ea16e23e661fc92259789f0ef53c91d2b6b972fd86ae874d9ac","source":{"kind":"arxiv","id":"2503.07833","version":1},"attestation_state":"computed","paper":{"title":"HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erchin Serpedin, Hasan Kurban, Samir Abdaljalil","submitted_at":"2025-03-10T20:24:07Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in various contexts, yet remain prone to generating non-factual content, commonly referred to as \"hallucinations\". The literature categorizes hallucinations into several types, including entity-level, relation-level, and sentence-level hallucinations. However, existing hallucination datasets often fail to capture fine-grained hallucinations in multilingual settings. In this work, we introduce HalluVerse25, a multilingual LLM hallucination dataset that categorizes fine-grained hallucinations in English, Arabic, and Turkish. Our dataset construc"},"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":"2503.07833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T20:24:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fca6853b6505b179362b7115b9e6a87e484b3eb0763cbea277299dbb787bf442","abstract_canon_sha256":"7179b7635073ace29f7920edd789bea8fe92e20864d186ead4bec54c8e5ce772"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:44.828944Z","signature_b64":"H2Ls0YqHtjwsb7VpJnMR/CKxiH18HRQ8VN/WDRM/RW5mbBTk8jkSQUz7MmwhoGXYxrUywmdmq9CmdOl+BKu+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"155cd2931c808ea16e23e661fc92259789f0ef53c91d2b6b972fd86ae874d9ac","last_reissued_at":"2026-07-05T10:28:44.828387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:44.828387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erchin Serpedin, Hasan Kurban, Samir Abdaljalil","submitted_at":"2025-03-10T20:24:07Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in various contexts, yet remain prone to generating non-factual content, commonly referred to as \"hallucinations\". The literature categorizes hallucinations into several types, including entity-level, relation-level, and sentence-level hallucinations. However, existing hallucination datasets often fail to capture fine-grained hallucinations in multilingual settings. In this work, we introduce HalluVerse25, a multilingual LLM hallucination dataset that categorizes fine-grained hallucinations in English, Arabic, and Turkish. Our dataset construc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07833","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/2503.07833/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":"2503.07833","created_at":"2026-07-05T10:28:44.828484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07833v1","created_at":"2026-07-05T10:28:44.828484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07833","created_at":"2026-07-05T10:28:44.828484+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVONFEY4QCHK","created_at":"2026-07-05T10:28:44.828484+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVONFEY4QCHKC3RD","created_at":"2026-07-05T10:28:44.828484+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVONFEY4","created_at":"2026-07-05T10:28:44.828484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07670","citing_title":"Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07833","citing_title":"Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17007","citing_title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07833","citing_title":"Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16909","citing_title":"PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6","json":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6.json","graph_json":"https://pith.science/api/pith-number/CVONFEY4QCHKC3RD4ZQ7ZERFS6/graph.json","events_json":"https://pith.science/api/pith-number/CVONFEY4QCHKC3RD4ZQ7ZERFS6/events.json","paper":"https://pith.science/paper/CVONFEY4"},"agent_actions":{"view_html":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6","download_json":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6.json","view_paper":"https://pith.science/paper/CVONFEY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07833&json=true","fetch_graph":"https://pith.science/api/pith-number/CVONFEY4QCHKC3RD4ZQ7ZERFS6/graph.json","fetch_events":"https://pith.science/api/pith-number/CVONFEY4QCHKC3RD4ZQ7ZERFS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6/action/storage_attestation","attest_author":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6/action/author_attestation","sign_citation":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6/action/citation_signature","submit_replication":"https://pith.science/pith/CVONFEY4QCHKC3RD4ZQ7ZERFS6/action/replication_record"}},"created_at":"2026-07-05T10:28:44.828484+00:00","updated_at":"2026-07-05T10:28:44.828484+00:00"}