{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORDBTZXLRJGGCBJFA2DCHX2PSQ","short_pith_number":"pith:ORDBTZXL","schema_version":"1.0","canonical_sha256":"744619e6eb8a4c610525068623df4f9417f6b25cee5b95edc36fa71c834aac35","source":{"kind":"arxiv","id":"2412.02946","version":1},"attestation_state":"computed","paper":{"title":"Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chin-Po Chen, Jeng-Lin Li, Ming-Ching Chang, Po-Hsuan Huang, Wei-Chao Chen","submitted_at":"2024-12-04T01:23:57Z","abstract_excerpt":"Recent advancements in large vision-language models (LVLM) have significantly enhanced their ability to comprehend visual inputs alongside natural language. However, a major challenge in their real-world application is hallucination, where LVLMs generate non-existent visual elements, eroding user trust. The underlying mechanism driving this multimodal hallucination is poorly understood. Minimal research has illuminated whether contexts such as sky, tree, or grass field involve the LVLM in hallucinating a frisbee. We hypothesize that hidden factors, such as objects, contexts, and semantic foreg"},"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":"2412.02946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T01:23:57Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"28ad814c78ceabeeae548c6084aefccb8b0d24db15480cc31539ebcc10e11287","abstract_canon_sha256":"91e9d4323d4fc42e246d9f00f35afbfff7701ae8f1af3766d44c2b08707e6550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:59.555439Z","signature_b64":"/bx79wtmX6+mkLiLorbRlJtajJYjnZDH5o8Hsnmd9m4bMSLEBc2Inv7PmNoFzR/OY0SWuBVCNk60/7u8FkudCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744619e6eb8a4c610525068623df4f9417f6b25cee5b95edc36fa71c834aac35","last_reissued_at":"2026-07-05T10:40:59.554856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:59.554856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chin-Po Chen, Jeng-Lin Li, Ming-Ching Chang, Po-Hsuan Huang, Wei-Chao Chen","submitted_at":"2024-12-04T01:23:57Z","abstract_excerpt":"Recent advancements in large vision-language models (LVLM) have significantly enhanced their ability to comprehend visual inputs alongside natural language. However, a major challenge in their real-world application is hallucination, where LVLMs generate non-existent visual elements, eroding user trust. The underlying mechanism driving this multimodal hallucination is poorly understood. Minimal research has illuminated whether contexts such as sky, tree, or grass field involve the LVLM in hallucinating a frisbee. We hypothesize that hidden factors, such as objects, contexts, and semantic foreg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02946","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/2412.02946/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":"2412.02946","created_at":"2026-07-05T10:40:59.554925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02946v1","created_at":"2026-07-05T10:40:59.554925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02946","created_at":"2026-07-05T10:40:59.554925+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORDBTZXLRJGG","created_at":"2026-07-05T10:40:59.554925+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORDBTZXLRJGGCBJF","created_at":"2026-07-05T10:40:59.554925+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORDBTZXL","created_at":"2026-07-05T10:40:59.554925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27596","citing_title":"Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ","json":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ.json","graph_json":"https://pith.science/api/pith-number/ORDBTZXLRJGGCBJFA2DCHX2PSQ/graph.json","events_json":"https://pith.science/api/pith-number/ORDBTZXLRJGGCBJFA2DCHX2PSQ/events.json","paper":"https://pith.science/paper/ORDBTZXL"},"agent_actions":{"view_html":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ","download_json":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ.json","view_paper":"https://pith.science/paper/ORDBTZXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02946&json=true","fetch_graph":"https://pith.science/api/pith-number/ORDBTZXLRJGGCBJFA2DCHX2PSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ORDBTZXLRJGGCBJFA2DCHX2PSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ/action/storage_attestation","attest_author":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ/action/author_attestation","sign_citation":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ/action/citation_signature","submit_replication":"https://pith.science/pith/ORDBTZXLRJGGCBJFA2DCHX2PSQ/action/replication_record"}},"created_at":"2026-07-05T10:40:59.554925+00:00","updated_at":"2026-07-05T10:40:59.554925+00:00"}