{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZREYCHY4Q7SDF2E42TCNRDNLNZ","short_pith_number":"pith:ZREYCHY4","schema_version":"1.0","canonical_sha256":"cc49811f1c87e432e89cd4c4d88dab6e73d44fd424d2f918f55ae17cbc55e7a1","source":{"kind":"arxiv","id":"2410.03176","version":1},"attestation_state":"computed","paper":{"title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aimin Zhou, Changzhi Sun, Tao Ji, Yuanbin Wu, Yufang Liu","submitted_at":"2024-10-04T06:24:49Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model these hallucinations originate from. In this paper, we present an in-depth investigation into the object hallucination problem specifically within the CLIP model, which serves as the backbone for many state-of-the-art vision-language systems. We unveil that even in isolation, the CLIP model is prone to object hallucinations, suggesting that the hallucination pro"},"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":"2410.03176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T06:24:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76866e7db68a889235b02effc8255ad3d926a847c90297565f71108a90872056","abstract_canon_sha256":"c2c5d10f35c15734642ba3c4f668399db49f8d3a6eece4d68409e511330eec32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:45.682293Z","signature_b64":"ZCE9I7wllcmXhJdvV1JkHCy3LUlOssNJeXUYIBw6dtKXI8mlJTiVZaPzwm+cQ/vyxADesnt7YatU5smNljFtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc49811f1c87e432e89cd4c4d88dab6e73d44fd424d2f918f55ae17cbc55e7a1","last_reissued_at":"2026-07-05T09:15:45.681810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:45.681810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aimin Zhou, Changzhi Sun, Tao Ji, Yuanbin Wu, Yufang Liu","submitted_at":"2024-10-04T06:24:49Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model these hallucinations originate from. In this paper, we present an in-depth investigation into the object hallucination problem specifically within the CLIP model, which serves as the backbone for many state-of-the-art vision-language systems. We unveil that even in isolation, the CLIP model is prone to object hallucinations, suggesting that the hallucination pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03176","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/2410.03176/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":"2410.03176","created_at":"2026-07-05T09:15:45.681873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03176v1","created_at":"2026-07-05T09:15:45.681873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03176","created_at":"2026-07-05T09:15:45.681873+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZREYCHY4Q7SD","created_at":"2026-07-05T09:15:45.681873+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZREYCHY4Q7SDF2E4","created_at":"2026-07-05T09:15:45.681873+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZREYCHY4","created_at":"2026-07-05T09:15:45.681873+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/ZREYCHY4Q7SDF2E42TCNRDNLNZ","json":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ.json","graph_json":"https://pith.science/api/pith-number/ZREYCHY4Q7SDF2E42TCNRDNLNZ/graph.json","events_json":"https://pith.science/api/pith-number/ZREYCHY4Q7SDF2E42TCNRDNLNZ/events.json","paper":"https://pith.science/paper/ZREYCHY4"},"agent_actions":{"view_html":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ","download_json":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ.json","view_paper":"https://pith.science/paper/ZREYCHY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03176&json=true","fetch_graph":"https://pith.science/api/pith-number/ZREYCHY4Q7SDF2E42TCNRDNLNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZREYCHY4Q7SDF2E42TCNRDNLNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZREYCHY4Q7SDF2E42TCNRDNLNZ/action/replication_record"}},"created_at":"2026-07-05T09:15:45.681873+00:00","updated_at":"2026-07-05T09:15:45.681873+00:00"}