{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ETPXKQOGYXZ7KNH63ZY44A5PLC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1fa837aba893519237d77a299e2b3dbc5815580c02cd8312991128b382e58bea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T09:30:02Z","title_canon_sha256":"ef6ef03795b323de41818da7ccef49be86fa39d4c18e4588f3a93e65d103747c"},"schema_version":"1.0","source":{"id":"2311.16479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16479","created_at":"2026-07-05T07:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16479v1","created_at":"2026-07-05T07:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16479","created_at":"2026-07-05T07:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"ETPXKQOGYXZ7","created_at":"2026-07-05T07:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"ETPXKQOGYXZ7KNH6","created_at":"2026-07-05T07:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"ETPXKQOG","created_at":"2026-07-05T07:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:4552cd0722c5e3e9f01038e59c7d9358c866cc87e0df48b4462435278c7ead59","target":"graph","created_at":"2026-07-05T07:17:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.16479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaoyang Zhao, Jinqiao Wang, Ming Tang, Yousong Zhu, Yufei Zhan, Zhaowen Li, Zhiyang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T09:30:02Z","title":"Mitigating Hallucination in Visual Language Models with Visual Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16479","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:18e57ad559e560f9e374d34f8baf4ba82aac52d4159f9790ea1f8ab8707c79fc","target":"record","created_at":"2026-07-05T07:17:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1fa837aba893519237d77a299e2b3dbc5815580c02cd8312991128b382e58bea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T09:30:02Z","title_canon_sha256":"ef6ef03795b323de41818da7ccef49be86fa39d4c18e4588f3a93e65d103747c"},"schema_version":"1.0","source":{"id":"2311.16479","kind":"arxiv","version":1}},"canonical_sha256":"24df7541c6c5f3f534fede71ce03af58a4d2cc34462b9e986764d784881e5062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24df7541c6c5f3f534fede71ce03af58a4d2cc34462b9e986764d784881e5062","first_computed_at":"2026-07-05T07:17:42.406784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:42.406784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqBeCaKOjRYb5VR+89wMMHgejqHoW1yw0hIiIO5rGHRrpDO73w+RtMJcdXZLImKNuwON2tjfzLI357M/A6udBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:42.407364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18e57ad559e560f9e374d34f8baf4ba82aac52d4159f9790ea1f8ab8707c79fc","sha256:4552cd0722c5e3e9f01038e59c7d9358c866cc87e0df48b4462435278c7ead59"],"state_sha256":"68bb3caea410e98d4af5f142502e641447ce3dec6745f92b3c8a171d451989ac"}