{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S3DPFVDYZFLXHTPA3M3WL663QP","short_pith_number":"pith:S3DPFVDY","schema_version":"1.0","canonical_sha256":"96c6f2d478c95773cde0db3765fbdb83fc5a57451422d5d778ae12ca5a8feee9","source":{"kind":"arxiv","id":"2402.11622","version":2},"attestation_state":"computed","paper":{"title":"Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ding Wang, Jinghao Zhang, Junfei Wu, Liang Wang, Qiang Liu, Shu Wu, Tieniu Tan","submitted_at":"2024-02-18T15:28:39Z","abstract_excerpt":"Object hallucination has been an Achilles' heel which hinders the broader applications of large vision-language models (LVLMs). Object hallucination refers to the phenomenon that the LVLMs claim non-existent objects in the image. To mitigate the object hallucinations, instruction tuning and external model-based detection methods have been proposed, which either require large-scare computational resources or depend on the detection result of external models. However, there remains an under-explored field to utilize the LVLM itself to alleviate object hallucinations. In this work, we adopt the i"},"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":"2402.11622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T15:28:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b93d0eb1627111f0f0e955c5313681eb4ca81caf1a89f04fbfc1f3144e2223f3","abstract_canon_sha256":"81ab5bc76e091d4e0d9839ed867f3a331bdffc121966d9aee5b503b587659c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:37.192758Z","signature_b64":"rLOCGLdkszI5RUAt5zjXzC4PMb9vIPRP6zRpFAwHU8g9nacU3cT/TPNZ+oG39Xlg5rMtTZUBxjxuN+LylnT4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96c6f2d478c95773cde0db3765fbdb83fc5a57451422d5d778ae12ca5a8feee9","last_reissued_at":"2026-07-05T08:37:37.192252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:37.192252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ding Wang, Jinghao Zhang, Junfei Wu, Liang Wang, Qiang Liu, Shu Wu, Tieniu Tan","submitted_at":"2024-02-18T15:28:39Z","abstract_excerpt":"Object hallucination has been an Achilles' heel which hinders the broader applications of large vision-language models (LVLMs). Object hallucination refers to the phenomenon that the LVLMs claim non-existent objects in the image. To mitigate the object hallucinations, instruction tuning and external model-based detection methods have been proposed, which either require large-scare computational resources or depend on the detection result of external models. However, there remains an under-explored field to utilize the LVLM itself to alleviate object hallucinations. In this work, we adopt the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11622","kind":"arxiv","version":2},"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/2402.11622/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":"2402.11622","created_at":"2026-07-05T08:37:37.192322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11622v2","created_at":"2026-07-05T08:37:37.192322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11622","created_at":"2026-07-05T08:37:37.192322+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3DPFVDYZFLX","created_at":"2026-07-05T08:37:37.192322+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3DPFVDYZFLXHTPA","created_at":"2026-07-05T08:37:37.192322+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3DPFVDY","created_at":"2026-07-05T08:37:37.192322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24602","citing_title":"Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16343","citing_title":"Visual Reasoning Agent: Robust Vision Systems in Remote Sensing via Inference-Time Scaling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":175,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP","json":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP.json","graph_json":"https://pith.science/api/pith-number/S3DPFVDYZFLXHTPA3M3WL663QP/graph.json","events_json":"https://pith.science/api/pith-number/S3DPFVDYZFLXHTPA3M3WL663QP/events.json","paper":"https://pith.science/paper/S3DPFVDY"},"agent_actions":{"view_html":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP","download_json":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP.json","view_paper":"https://pith.science/paper/S3DPFVDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11622&json=true","fetch_graph":"https://pith.science/api/pith-number/S3DPFVDYZFLXHTPA3M3WL663QP/graph.json","fetch_events":"https://pith.science/api/pith-number/S3DPFVDYZFLXHTPA3M3WL663QP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP/action/storage_attestation","attest_author":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP/action/author_attestation","sign_citation":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP/action/citation_signature","submit_replication":"https://pith.science/pith/S3DPFVDYZFLXHTPA3M3WL663QP/action/replication_record"}},"created_at":"2026-07-05T08:37:37.192322+00:00","updated_at":"2026-07-05T08:37:37.192322+00:00"}