{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BRWNS7AIQQTESBH54AP2VAVUTP","short_pith_number":"pith:BRWNS7AI","schema_version":"1.0","canonical_sha256":"0c6cd97c0884264904fde01faa82b49bc5900080562db1955a5a6f6564ac7fcf","source":{"kind":"arxiv","id":"2505.17529","version":1},"attestation_state":"computed","paper":{"title":"Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Keonwoo Kim, Sungzoon Cho, Taebaek Hwang, Yeongjae Cho","submitted_at":"2025-05-23T06:35:43Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models (LVLMs) have significantly expanded their utility in tasks like image captioning and visual question answering. However, they still struggle with object hallucination, where models generate descriptions that inaccurately reflect the visual content by including nonexistent objects or misrepresenting existing ones. While previous methods, such as data augmentation and training-free approaches, strive to tackle this issue, they still encounter scalability challenges and often depend on additional external modules. In this work, we propose Ensemb"},"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":"2505.17529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T06:35:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e380abd0cc485d9d7d9ceb22e259915c1c35ff695deab3157f600017af716e52","abstract_canon_sha256":"b4fddd4beac664b3516b5283d49bf3f8e4e61d073eaf8e66504a4fcec4e97507"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:27.704171Z","signature_b64":"QwG6a+Mf/m7iCHBZV8sFDrykzsSOPef6rpZ+xFdsJhYSVSBJ9x5LI1qm3dv0WUoqvFUNYa2ywMAmrp1QPxbOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6cd97c0884264904fde01faa82b49bc5900080562db1955a5a6f6564ac7fcf","last_reissued_at":"2026-07-05T11:08:27.703668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:27.703668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Keonwoo Kim, Sungzoon Cho, Taebaek Hwang, Yeongjae Cho","submitted_at":"2025-05-23T06:35:43Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models (LVLMs) have significantly expanded their utility in tasks like image captioning and visual question answering. However, they still struggle with object hallucination, where models generate descriptions that inaccurately reflect the visual content by including nonexistent objects or misrepresenting existing ones. While previous methods, such as data augmentation and training-free approaches, strive to tackle this issue, they still encounter scalability challenges and often depend on additional external modules. In this work, we propose Ensemb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17529","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/2505.17529/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":"2505.17529","created_at":"2026-07-05T11:08:27.703718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17529v1","created_at":"2026-07-05T11:08:27.703718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17529","created_at":"2026-07-05T11:08:27.703718+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRWNS7AIQQTE","created_at":"2026-07-05T11:08:27.703718+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRWNS7AIQQTESBH5","created_at":"2026-07-05T11:08:27.703718+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRWNS7AI","created_at":"2026-07-05T11:08:27.703718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29805","citing_title":"Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31054","citing_title":"ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs","ref_index":3,"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12424","citing_title":"Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":289,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP","json":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP.json","graph_json":"https://pith.science/api/pith-number/BRWNS7AIQQTESBH54AP2VAVUTP/graph.json","events_json":"https://pith.science/api/pith-number/BRWNS7AIQQTESBH54AP2VAVUTP/events.json","paper":"https://pith.science/paper/BRWNS7AI"},"agent_actions":{"view_html":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP","download_json":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP.json","view_paper":"https://pith.science/paper/BRWNS7AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17529&json=true","fetch_graph":"https://pith.science/api/pith-number/BRWNS7AIQQTESBH54AP2VAVUTP/graph.json","fetch_events":"https://pith.science/api/pith-number/BRWNS7AIQQTESBH54AP2VAVUTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP/action/storage_attestation","attest_author":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP/action/author_attestation","sign_citation":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP/action/citation_signature","submit_replication":"https://pith.science/pith/BRWNS7AIQQTESBH54AP2VAVUTP/action/replication_record"}},"created_at":"2026-07-05T11:08:27.703718+00:00","updated_at":"2026-07-05T11:08:27.703718+00:00"}