{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OVDKV3IVXFAPUXB54HUVLUP6EA","short_pith_number":"pith:OVDKV3IV","schema_version":"1.0","canonical_sha256":"7546aaed15b940fa5c3de1e955d1fe202d341ac662fba46c02618bb6b8b19d50","source":{"kind":"arxiv","id":"2404.13874","version":4},"attestation_state":"computed","paper":{"title":"VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyi Qiu, Nanyun Peng, Wenbo Hu, Zi-Yi Dou","submitted_at":"2024-04-22T04:49:22Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs, undermining their reliability. A comprehensive quantitative evaluation is necessary to identify and understand the extent of hallucinations in these models. However, existing benchmarks are often limited in scope, focusing mainly on object hallucinations. Furthermore, current evaluation methods struggle to effectively address the subtle semantic distinctions between model outputs and reference data, as well as the balance between hallucination a"},"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":"2404.13874","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T04:49:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ed0dedd1632be355fb6bd6cddf1a1c1a73117057901f9a92a2aa6e93528bc431","abstract_canon_sha256":"650b6fdba73322771c8d7aa0ca77df26a4c4d5db7293433da69613ddef0a8987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:31.587585Z","signature_b64":"CrzX3LgvgLTjqQIr/ShXMwHrH7lO+Vc5qKAv0o/eUiIQNO2jwwMAnsZJjq1jRSdcg6xrQI/awtmEo+QyQ4UECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7546aaed15b940fa5c3de1e955d1fe202d341ac662fba46c02618bb6b8b19d50","last_reissued_at":"2026-07-05T09:15:31.586941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:31.586941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyi Qiu, Nanyun Peng, Wenbo Hu, Zi-Yi Dou","submitted_at":"2024-04-22T04:49:22Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs, undermining their reliability. A comprehensive quantitative evaluation is necessary to identify and understand the extent of hallucinations in these models. However, existing benchmarks are often limited in scope, focusing mainly on object hallucinations. Furthermore, current evaluation methods struggle to effectively address the subtle semantic distinctions between model outputs and reference data, as well as the balance between hallucination a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13874","kind":"arxiv","version":4},"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/2404.13874/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":"2404.13874","created_at":"2026-07-05T09:15:31.587035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13874v4","created_at":"2026-07-05T09:15:31.587035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13874","created_at":"2026-07-05T09:15:31.587035+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVDKV3IVXFAP","created_at":"2026-07-05T09:15:31.587035+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVDKV3IVXFAPUXB5","created_at":"2026-07-05T09:15:31.587035+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVDKV3IV","created_at":"2026-07-05T09:15:31.587035+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/OVDKV3IVXFAPUXB54HUVLUP6EA","json":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA.json","graph_json":"https://pith.science/api/pith-number/OVDKV3IVXFAPUXB54HUVLUP6EA/graph.json","events_json":"https://pith.science/api/pith-number/OVDKV3IVXFAPUXB54HUVLUP6EA/events.json","paper":"https://pith.science/paper/OVDKV3IV"},"agent_actions":{"view_html":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA","download_json":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA.json","view_paper":"https://pith.science/paper/OVDKV3IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13874&json=true","fetch_graph":"https://pith.science/api/pith-number/OVDKV3IVXFAPUXB54HUVLUP6EA/graph.json","fetch_events":"https://pith.science/api/pith-number/OVDKV3IVXFAPUXB54HUVLUP6EA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA/action/storage_attestation","attest_author":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA/action/author_attestation","sign_citation":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA/action/citation_signature","submit_replication":"https://pith.science/pith/OVDKV3IVXFAPUXB54HUVLUP6EA/action/replication_record"}},"created_at":"2026-07-05T09:15:31.587035+00:00","updated_at":"2026-07-05T09:15:31.587035+00:00"}