{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IH7GTO5MH7FXIJFNF5ZBPPK76Q","short_pith_number":"pith:IH7GTO5M","schema_version":"1.0","canonical_sha256":"41fe69bbac3fcb7424ad2f7217bd5ff41881e12e5615f7e1c31c0a344a02dd6f","source":{"kind":"arxiv","id":"2403.08776","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fatma Shalabi, Hichem Felouat, Huy H. Nguyen, Isao Echizen","submitted_at":"2024-01-22T13:54:40Z","abstract_excerpt":"Out-of-context (OOC) detection is a challenging task involving identifying images and texts that are irrelevant to the context in which they are presented. Large vision-language models (LVLMs) are effective at various tasks, including image classification and text generation. However, the extent of their proficiency in multimodal OOC detection tasks is unclear. In this paper, we investigate the ability of LVLMs to detect multimodal OOC and show that these models cannot achieve high accuracy on OOC detection tasks without fine-tuning. However, we demonstrate that fine-tuning LVLMs on multimodal"},"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":"2403.08776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T13:54:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"218367a1a3f26037b336f6a6750900ec521f09a13a90633691f688c499929544","abstract_canon_sha256":"125da964aa0d6ca81463a77aeb942ddd45ce6d422b877e2037b6c7b4f956d4d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:46.831827Z","signature_b64":"uI9AtjbVA7m0RD5uNY5ClCBB5N5PaKCj4/YgJNHB0OiqDw5H7V4gxKhNmL6FiXifmC/PZot6OLR9OXIMgybLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41fe69bbac3fcb7424ad2f7217bd5ff41881e12e5615f7e1c31c0a344a02dd6f","last_reissued_at":"2026-07-05T07:55:46.831368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:46.831368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fatma Shalabi, Hichem Felouat, Huy H. Nguyen, Isao Echizen","submitted_at":"2024-01-22T13:54:40Z","abstract_excerpt":"Out-of-context (OOC) detection is a challenging task involving identifying images and texts that are irrelevant to the context in which they are presented. Large vision-language models (LVLMs) are effective at various tasks, including image classification and text generation. However, the extent of their proficiency in multimodal OOC detection tasks is unclear. In this paper, we investigate the ability of LVLMs to detect multimodal OOC and show that these models cannot achieve high accuracy on OOC detection tasks without fine-tuning. However, we demonstrate that fine-tuning LVLMs on multimodal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08776","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/2403.08776/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":"2403.08776","created_at":"2026-07-05T07:55:46.831425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08776v1","created_at":"2026-07-05T07:55:46.831425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08776","created_at":"2026-07-05T07:55:46.831425+00:00"},{"alias_kind":"pith_short_12","alias_value":"IH7GTO5MH7FX","created_at":"2026-07-05T07:55:46.831425+00:00"},{"alias_kind":"pith_short_16","alias_value":"IH7GTO5MH7FXIJFN","created_at":"2026-07-05T07:55:46.831425+00:00"},{"alias_kind":"pith_short_8","alias_value":"IH7GTO5M","created_at":"2026-07-05T07:55:46.831425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q","json":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q.json","graph_json":"https://pith.science/api/pith-number/IH7GTO5MH7FXIJFNF5ZBPPK76Q/graph.json","events_json":"https://pith.science/api/pith-number/IH7GTO5MH7FXIJFNF5ZBPPK76Q/events.json","paper":"https://pith.science/paper/IH7GTO5M"},"agent_actions":{"view_html":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q","download_json":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q.json","view_paper":"https://pith.science/paper/IH7GTO5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08776&json=true","fetch_graph":"https://pith.science/api/pith-number/IH7GTO5MH7FXIJFNF5ZBPPK76Q/graph.json","fetch_events":"https://pith.science/api/pith-number/IH7GTO5MH7FXIJFNF5ZBPPK76Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q/action/storage_attestation","attest_author":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q/action/author_attestation","sign_citation":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q/action/citation_signature","submit_replication":"https://pith.science/pith/IH7GTO5MH7FXIJFNF5ZBPPK76Q/action/replication_record"}},"created_at":"2026-07-05T07:55:46.831425+00:00","updated_at":"2026-07-05T07:55:46.831425+00:00"}