{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZDLPCTKAN2HRTROPIQEVRRAST4","short_pith_number":"pith:ZDLPCTKA","schema_version":"1.0","canonical_sha256":"c8d6f14d406e8f19c5cf440958c4129f328cc3fc281696a13cf2731f15dc2377","source":{"kind":"arxiv","id":"2412.05155","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cagri Coltekin, Pinar Karagoz, Recep Firat Cekinel","submitted_at":"2024-12-06T16:13:19Z","abstract_excerpt":"This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking. To be more specific, we investigate whether incorporating multimodal content improves performance compared to text-only models and how well VLMs utilize text and image information to enhance misinformation detection. Furthermore we propose a probing classifier based solution using VLMs. Our approach extracts embeddings from the last hidden layer of selected VLMs and inputs them into a neural probing classifier for multi-class veracity classification. Throu"},"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":"2412.05155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T16:13:19Z","cross_cats_sorted":[],"title_canon_sha256":"5eb331985d28378352c1c7dac6f05859d71b07ae000d5accfa5d55f7ca606ae1","abstract_canon_sha256":"f76708e77d36a8fcc510029b13205e8c3608d8282b47f0040481c915cd682ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:29.505299Z","signature_b64":"Buo27XmJ5Ggsn7BZK7lJqAeC3OXr8Gp6l8kqFMIAo/QqT9fyNCwULI4hWk5tdLiX1sUV9Vti1STQUJQ3N6yiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8d6f14d406e8f19c5cf440958c4129f328cc3fc281696a13cf2731f15dc2377","last_reissued_at":"2026-07-05T09:45:29.504913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:29.504913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cagri Coltekin, Pinar Karagoz, Recep Firat Cekinel","submitted_at":"2024-12-06T16:13:19Z","abstract_excerpt":"This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking. To be more specific, we investigate whether incorporating multimodal content improves performance compared to text-only models and how well VLMs utilize text and image information to enhance misinformation detection. Furthermore we propose a probing classifier based solution using VLMs. Our approach extracts embeddings from the last hidden layer of selected VLMs and inputs them into a neural probing classifier for multi-class veracity classification. Throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05155","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/2412.05155/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":"2412.05155","created_at":"2026-07-05T09:45:29.504969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05155v1","created_at":"2026-07-05T09:45:29.504969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05155","created_at":"2026-07-05T09:45:29.504969+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDLPCTKAN2HR","created_at":"2026-07-05T09:45:29.504969+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDLPCTKAN2HRTROP","created_at":"2026-07-05T09:45:29.504969+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDLPCTKA","created_at":"2026-07-05T09:45:29.504969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13038","citing_title":"HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4","json":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4.json","graph_json":"https://pith.science/api/pith-number/ZDLPCTKAN2HRTROPIQEVRRAST4/graph.json","events_json":"https://pith.science/api/pith-number/ZDLPCTKAN2HRTROPIQEVRRAST4/events.json","paper":"https://pith.science/paper/ZDLPCTKA"},"agent_actions":{"view_html":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4","download_json":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4.json","view_paper":"https://pith.science/paper/ZDLPCTKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05155&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDLPCTKAN2HRTROPIQEVRRAST4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDLPCTKAN2HRTROPIQEVRRAST4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4/action/storage_attestation","attest_author":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4/action/author_attestation","sign_citation":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4/action/citation_signature","submit_replication":"https://pith.science/pith/ZDLPCTKAN2HRTROPIQEVRRAST4/action/replication_record"}},"created_at":"2026-07-05T09:45:29.504969+00:00","updated_at":"2026-07-05T09:45:29.504969+00:00"}