{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GKCX3DHPNDP7XTGSIONP44A4Q7","short_pith_number":"pith:GKCX3DHP","schema_version":"1.0","canonical_sha256":"32857d8cef68dffbccd2439afe701c87d8adaad665085c9b9b3dcad20c9ee91c","source":{"kind":"arxiv","id":"2407.06192","version":2},"attestation_state":"computed","paper":{"title":"Multi-Object Hallucination in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"David F. Fouhey, Jianing Yang, Joyce Chai, Shengyi Qian, Sihan Xu, Xuejun Zhang, Xuweiyi Chen, Ziqiao Ma","submitted_at":"2024-07-08T17:59:57Z","abstract_excerpt":"Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination primarily concentrate on the presence of a single object class rather than individual entities, this work systematically investigates multi-object hallucination, examining how models misperceive (e.g., invent nonexistent objects or become distracted) when tasked with focusing on multiple objects simultaneously. We introduce Recognition-based Object Probing Evaluation (ROPE), an automated evaluation protocol that consid"},"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":"2407.06192","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T17:59:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dfba89cfad6b8a3481b893d0910f597b4c953f3469e5ab1542fe1e3d0bbbf486","abstract_canon_sha256":"fc81a5c46fe3967a68f7adfa71187e7cee0a041e940181d0e17415c8c080707f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:31.496124Z","signature_b64":"YSLyhyKtN6uPkO07+8g4rjwz30/NHMDGJbzqMsn4qLF8X86nlK74mfBqmd/a2kBQUiFO5DycGHK8BxjN+RyHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32857d8cef68dffbccd2439afe701c87d8adaad665085c9b9b3dcad20c9ee91c","last_reissued_at":"2026-07-05T09:29:31.495611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:31.495611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Object Hallucination in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"David F. Fouhey, Jianing Yang, Joyce Chai, Shengyi Qian, Sihan Xu, Xuejun Zhang, Xuweiyi Chen, Ziqiao Ma","submitted_at":"2024-07-08T17:59:57Z","abstract_excerpt":"Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination primarily concentrate on the presence of a single object class rather than individual entities, this work systematically investigates multi-object hallucination, examining how models misperceive (e.g., invent nonexistent objects or become distracted) when tasked with focusing on multiple objects simultaneously. We introduce Recognition-based Object Probing Evaluation (ROPE), an automated evaluation protocol that consid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06192","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/2407.06192/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":"2407.06192","created_at":"2026-07-05T09:29:31.495670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06192v2","created_at":"2026-07-05T09:29:31.495670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06192","created_at":"2026-07-05T09:29:31.495670+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKCX3DHPNDP7","created_at":"2026-07-05T09:29:31.495670+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKCX3DHPNDP7XTGS","created_at":"2026-07-05T09:29:31.495670+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKCX3DHP","created_at":"2026-07-05T09:29:31.495670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7","json":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7.json","graph_json":"https://pith.science/api/pith-number/GKCX3DHPNDP7XTGSIONP44A4Q7/graph.json","events_json":"https://pith.science/api/pith-number/GKCX3DHPNDP7XTGSIONP44A4Q7/events.json","paper":"https://pith.science/paper/GKCX3DHP"},"agent_actions":{"view_html":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7","download_json":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7.json","view_paper":"https://pith.science/paper/GKCX3DHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06192&json=true","fetch_graph":"https://pith.science/api/pith-number/GKCX3DHPNDP7XTGSIONP44A4Q7/graph.json","fetch_events":"https://pith.science/api/pith-number/GKCX3DHPNDP7XTGSIONP44A4Q7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7/action/storage_attestation","attest_author":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7/action/author_attestation","sign_citation":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7/action/citation_signature","submit_replication":"https://pith.science/pith/GKCX3DHPNDP7XTGSIONP44A4Q7/action/replication_record"}},"created_at":"2026-07-05T09:29:31.495670+00:00","updated_at":"2026-07-05T09:29:31.495670+00:00"}