{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:65B75BXJ7URFZLQSNQHAXCKDUC","short_pith_number":"pith:65B75BXJ","schema_version":"1.0","canonical_sha256":"f743fe86e9fd225cae126c0e0b8943a0abc98a00aec131a56cd1ce7b09f37d0c","source":{"kind":"arxiv","id":"2508.03469","version":1},"attestation_state":"computed","paper":{"title":"IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhang Cui, Jiabing Yang, Liang Wang, Peng Xia, Tao Yu, Yan Huang, Ying Wei, Yixiang Chen, Yiyang Zhou","submitted_at":"2025-08-05T14:05:15Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress across multiple domains. However, these models still face the inherent challenge of integrating vision and language for collaborative inference, which often leads to \"hallucinations\", outputs that are not grounded in the corresponding images. Many efforts have been made to address these issues, but each comes with its own limitations, such as high computational cost or expensive dataset annotation. Recent research shows that LVLMs exhibit a long-term bias where hallucinations increase as the sequ"},"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":"2508.03469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T14:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"18cf1935dca999a79b1ff787e3b0b246d8601edcd64bffe133b7d523ba090fbb","abstract_canon_sha256":"54160b98b1f0f3f72eb8775abf17dfab58ccb73f3866fc0b701eff8253dc8fe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:56.859703Z","signature_b64":"w1kLEr9wbwEgxtlJ4PJQ077jjIHjwP3J5QXXfdAwMX/Dy/6Nr1AB6QXdj+NdLG5S/l+M4hchv4g2d/YeolOSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f743fe86e9fd225cae126c0e0b8943a0abc98a00aec131a56cd1ce7b09f37d0c","last_reissued_at":"2026-07-05T11:48:56.859208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:56.859208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhang Cui, Jiabing Yang, Liang Wang, Peng Xia, Tao Yu, Yan Huang, Ying Wei, Yixiang Chen, Yiyang Zhou","submitted_at":"2025-08-05T14:05:15Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress across multiple domains. However, these models still face the inherent challenge of integrating vision and language for collaborative inference, which often leads to \"hallucinations\", outputs that are not grounded in the corresponding images. Many efforts have been made to address these issues, but each comes with its own limitations, such as high computational cost or expensive dataset annotation. Recent research shows that LVLMs exhibit a long-term bias where hallucinations increase as the sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03469","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/2508.03469/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":"2508.03469","created_at":"2026-07-05T11:48:56.859281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03469v1","created_at":"2026-07-05T11:48:56.859281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03469","created_at":"2026-07-05T11:48:56.859281+00:00"},{"alias_kind":"pith_short_12","alias_value":"65B75BXJ7URF","created_at":"2026-07-05T11:48:56.859281+00:00"},{"alias_kind":"pith_short_16","alias_value":"65B75BXJ7URFZLQS","created_at":"2026-07-05T11:48:56.859281+00:00"},{"alias_kind":"pith_short_8","alias_value":"65B75BXJ","created_at":"2026-07-05T11:48:56.859281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00465","citing_title":"StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC","json":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC.json","graph_json":"https://pith.science/api/pith-number/65B75BXJ7URFZLQSNQHAXCKDUC/graph.json","events_json":"https://pith.science/api/pith-number/65B75BXJ7URFZLQSNQHAXCKDUC/events.json","paper":"https://pith.science/paper/65B75BXJ"},"agent_actions":{"view_html":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC","download_json":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC.json","view_paper":"https://pith.science/paper/65B75BXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03469&json=true","fetch_graph":"https://pith.science/api/pith-number/65B75BXJ7URFZLQSNQHAXCKDUC/graph.json","fetch_events":"https://pith.science/api/pith-number/65B75BXJ7URFZLQSNQHAXCKDUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC/action/storage_attestation","attest_author":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC/action/author_attestation","sign_citation":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC/action/citation_signature","submit_replication":"https://pith.science/pith/65B75BXJ7URFZLQSNQHAXCKDUC/action/replication_record"}},"created_at":"2026-07-05T11:48:56.859281+00:00","updated_at":"2026-07-05T11:48:56.859281+00:00"}