{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q74DGLTP2LPQCTSBPFJRFPGFO7","short_pith_number":"pith:Q74DGLTP","schema_version":"1.0","canonical_sha256":"87f8332e6fd2df014e41795312bcc577ef8855e56027cd3bb283ad78061fb86c","source":{"kind":"arxiv","id":"2311.16922","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Guanzheng Chen, Hang Zhang, Lidong Bing, Shijian Lu, Sicong Leng, Xin Li","submitted_at":"2023-11-28T16:26:35Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. Despite their success, LVLMs still suffer from the issue of object hallucinations, where models generate plausible yet incorrect outputs that include objects that do not exist in the images. To mitigate this issue, we introduce Visual Contrastive Decoding (VCD), a simple and training-free method that contrasts output distributions derived from original and distorted visual inputs. The proposed VC"},"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":"2311.16922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T16:26:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f27bccf9091d434ff1df100491de5b5ae81d234a1b0a71a87df63fd0b2bb329b","abstract_canon_sha256":"86fa5399ef54ad82de9ce3c17f9893dcc656fc5c6f1962c3f7a09efeecddb29b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:48.383120Z","signature_b64":"cplFM0b1VUtNraxaEEtRX2a0Ij6LEF0Sm1dnbuPQMLTf4uNysOwpSEbDiTFuqZdd6Y1lcJ3rNl2k6ITDo2GPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87f8332e6fd2df014e41795312bcc577ef8855e56027cd3bb283ad78061fb86c","last_reissued_at":"2026-07-05T07:17:48.382524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:48.382524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Guanzheng Chen, Hang Zhang, Lidong Bing, Shijian Lu, Sicong Leng, Xin Li","submitted_at":"2023-11-28T16:26:35Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. Despite their success, LVLMs still suffer from the issue of object hallucinations, where models generate plausible yet incorrect outputs that include objects that do not exist in the images. To mitigate this issue, we introduce Visual Contrastive Decoding (VCD), a simple and training-free method that contrasts output distributions derived from original and distorted visual inputs. The proposed VC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16922","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/2311.16922/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":"2311.16922","created_at":"2026-07-05T07:17:48.382616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16922v1","created_at":"2026-07-05T07:17:48.382616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16922","created_at":"2026-07-05T07:17:48.382616+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q74DGLTP2LPQ","created_at":"2026-07-05T07:17:48.382616+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q74DGLTP2LPQCTSB","created_at":"2026-07-05T07:17:48.382616+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q74DGLTP","created_at":"2026-07-05T07:17:48.382616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00247","citing_title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29805","citing_title":"Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29805","citing_title":"Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27993","citing_title":"Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30911","citing_title":"What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10292","citing_title":"Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12485","citing_title":"Letting the neural code speak: Automated characterization of monkey visual neurons through human language","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19250","citing_title":"Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15300","citing_title":"Deep Pre-Alignment for VLMs","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13868","citing_title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2402.11411","citing_title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17729","citing_title":"SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01840","citing_title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12485","citing_title":"Letting the neural code speak: Automated characterization of monkey visual neurons through human language","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26614","citing_title":"State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06679","citing_title":"Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":262,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7","json":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7.json","graph_json":"https://pith.science/api/pith-number/Q74DGLTP2LPQCTSBPFJRFPGFO7/graph.json","events_json":"https://pith.science/api/pith-number/Q74DGLTP2LPQCTSBPFJRFPGFO7/events.json","paper":"https://pith.science/paper/Q74DGLTP"},"agent_actions":{"view_html":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7","download_json":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7.json","view_paper":"https://pith.science/paper/Q74DGLTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16922&json=true","fetch_graph":"https://pith.science/api/pith-number/Q74DGLTP2LPQCTSBPFJRFPGFO7/graph.json","fetch_events":"https://pith.science/api/pith-number/Q74DGLTP2LPQCTSBPFJRFPGFO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7/action/storage_attestation","attest_author":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7/action/author_attestation","sign_citation":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7/action/citation_signature","submit_replication":"https://pith.science/pith/Q74DGLTP2LPQCTSBPFJRFPGFO7/action/replication_record"}},"created_at":"2026-07-05T07:17:48.382616+00:00","updated_at":"2026-07-05T07:17:48.382616+00:00"}