{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ETPXKQOGYXZ7KNH63ZY44A5PLC","short_pith_number":"pith:ETPXKQOG","schema_version":"1.0","canonical_sha256":"24df7541c6c5f3f534fede71ce03af58a4d2cc34462b9e986764d784881e5062","source":{"kind":"arxiv","id":"2311.16479","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Hallucination in Visual Language Models with Visual Supervision","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Zhao, Jinqiao Wang, Ming Tang, Yousong Zhu, Yufei Zhan, Zhaowen Li, Zhiyang Chen","submitted_at":"2023-11-27T09:30:02Z","abstract_excerpt":"Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a multi-modal context, which can be mainly attributed to two factors in training data and loss function. The vision instruction dataset primarily focuses on global description, and the auto-regressive loss function favors text modeling rather than image understanding. In this paper, we bring more detailed vision annotations and more discriminative vision models to facil"},"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":"2311.16479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T09:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"ef6ef03795b323de41818da7ccef49be86fa39d4c18e4588f3a93e65d103747c","abstract_canon_sha256":"1fa837aba893519237d77a299e2b3dbc5815580c02cd8312991128b382e58bea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:42.407364Z","signature_b64":"wqBeCaKOjRYb5VR+89wMMHgejqHoW1yw0hIiIO5rGHRrpDO73w+RtMJcdXZLImKNuwON2tjfzLI357M/A6udBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24df7541c6c5f3f534fede71ce03af58a4d2cc34462b9e986764d784881e5062","last_reissued_at":"2026-07-05T07:17:42.406784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:42.406784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Hallucination in Visual Language Models with Visual Supervision","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Zhao, Jinqiao Wang, Ming Tang, Yousong Zhu, Yufei Zhan, Zhaowen Li, Zhiyang Chen","submitted_at":"2023-11-27T09:30:02Z","abstract_excerpt":"Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a multi-modal context, which can be mainly attributed to two factors in training data and loss function. The vision instruction dataset primarily focuses on global description, and the auto-regressive loss function favors text modeling rather than image understanding. In this paper, we bring more detailed vision annotations and more discriminative vision models to facil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16479","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/2311.16479/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":"2311.16479","created_at":"2026-07-05T07:17:42.406864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16479v1","created_at":"2026-07-05T07:17:42.406864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16479","created_at":"2026-07-05T07:17:42.406864+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETPXKQOGYXZ7","created_at":"2026-07-05T07:17:42.406864+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETPXKQOGYXZ7KNH6","created_at":"2026-07-05T07:17:42.406864+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETPXKQOG","created_at":"2026-07-05T07:17:42.406864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29847","citing_title":"See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26656","citing_title":"DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00622","citing_title":"MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC","json":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC.json","graph_json":"https://pith.science/api/pith-number/ETPXKQOGYXZ7KNH63ZY44A5PLC/graph.json","events_json":"https://pith.science/api/pith-number/ETPXKQOGYXZ7KNH63ZY44A5PLC/events.json","paper":"https://pith.science/paper/ETPXKQOG"},"agent_actions":{"view_html":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC","download_json":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC.json","view_paper":"https://pith.science/paper/ETPXKQOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16479&json=true","fetch_graph":"https://pith.science/api/pith-number/ETPXKQOGYXZ7KNH63ZY44A5PLC/graph.json","fetch_events":"https://pith.science/api/pith-number/ETPXKQOGYXZ7KNH63ZY44A5PLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC/action/storage_attestation","attest_author":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC/action/author_attestation","sign_citation":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC/action/citation_signature","submit_replication":"https://pith.science/pith/ETPXKQOGYXZ7KNH63ZY44A5PLC/action/replication_record"}},"created_at":"2026-07-05T07:17:42.406864+00:00","updated_at":"2026-07-05T07:17:42.406864+00:00"}