{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MHW33XBFYGGFIDSM3DKXG2VX6L","short_pith_number":"pith:MHW33XBF","schema_version":"1.0","canonical_sha256":"61edbddc25c18c540e4cd8d5736ab7f2fc4cbe5ee7040cb5f52c96935c904e18","source":{"kind":"arxiv","id":"2402.15721","version":2},"attestation_state":"computed","paper":{"title":"Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chaoya Jiang, Haiyang Xu, Hongrui Jia, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-02-24T05:14:52Z","abstract_excerpt":"Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions. Previous hallucination evaluation studies on LVLMs have identified hallucinations in terms of objects, attributes, and relations but overlooked complex hallucinations that create an entire narrative around a fictional entity. In this paper, we introduce a refined taxonomy of hallucinations, featuring a new category: Event Hallucination. We then utilize advanced LLMs to generate and filter fine grained hallucinatory data consisting of various types"},"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":"2402.15721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-24T05:14:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a27feb3ef3750a187810857027ce8e84cd9e35431603e7c28b8f3f28fbf47a3b","abstract_canon_sha256":"3ea7c9f78e52ce91606637a3acf73182fa0c1b3e97d5427bf6238ff68de1ea7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:42.309567Z","signature_b64":"QHkUkf7lABflLZEHpz0TAmhVsgW2K5wyYSpyX3TzQmHTtjS7wipS2DAaHNa0ZTIup81C/6tRjvXLWtpBLj5EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61edbddc25c18c540e4cd8d5736ab7f2fc4cbe5ee7040cb5f52c96935c904e18","last_reissued_at":"2026-07-05T09:32:42.309010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:42.309010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chaoya Jiang, Haiyang Xu, Hongrui Jia, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-02-24T05:14:52Z","abstract_excerpt":"Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions. Previous hallucination evaluation studies on LVLMs have identified hallucinations in terms of objects, attributes, and relations but overlooked complex hallucinations that create an entire narrative around a fictional entity. In this paper, we introduce a refined taxonomy of hallucinations, featuring a new category: Event Hallucination. We then utilize advanced LLMs to generate and filter fine grained hallucinatory data consisting of various types"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15721","kind":"arxiv","version":2},"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/2402.15721/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":"2402.15721","created_at":"2026-07-05T09:32:42.309078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15721v2","created_at":"2026-07-05T09:32:42.309078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15721","created_at":"2026-07-05T09:32:42.309078+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHW33XBFYGGF","created_at":"2026-07-05T09:32:42.309078+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHW33XBFYGGFIDSM","created_at":"2026-07-05T09:32:42.309078+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHW33XBF","created_at":"2026-07-05T09:32:42.309078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L","json":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L.json","graph_json":"https://pith.science/api/pith-number/MHW33XBFYGGFIDSM3DKXG2VX6L/graph.json","events_json":"https://pith.science/api/pith-number/MHW33XBFYGGFIDSM3DKXG2VX6L/events.json","paper":"https://pith.science/paper/MHW33XBF"},"agent_actions":{"view_html":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L","download_json":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L.json","view_paper":"https://pith.science/paper/MHW33XBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15721&json=true","fetch_graph":"https://pith.science/api/pith-number/MHW33XBFYGGFIDSM3DKXG2VX6L/graph.json","fetch_events":"https://pith.science/api/pith-number/MHW33XBFYGGFIDSM3DKXG2VX6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L/action/storage_attestation","attest_author":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L/action/author_attestation","sign_citation":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L/action/citation_signature","submit_replication":"https://pith.science/pith/MHW33XBFYGGFIDSM3DKXG2VX6L/action/replication_record"}},"created_at":"2026-07-05T09:32:42.309078+00:00","updated_at":"2026-07-05T09:32:42.309078+00:00"}