{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQNI4JEIJMGAV2Z5IBDOLURDQG","short_pith_number":"pith:RQNI4JEI","schema_version":"1.0","canonical_sha256":"8c1a8e24884b0c0aeb3d4046e5d22381b511402dcd32333cd330243b3a53a0b1","source":{"kind":"arxiv","id":"2509.04714","version":1},"attestation_state":"computed","paper":{"title":"ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Wajiha Naveed, Zafar Ayyub Qazi, Zartash Afzal Uzmi","submitted_at":"2025-09-05T00:02:17Z","abstract_excerpt":"Misleading video thumbnails on platforms like YouTube are a pervasive problem, undermining user trust and platform integrity. This paper proposes a novel multi-modal detection pipeline that uses Large Language Models (LLMs) to flag misleading thumbnails. We first construct a comprehensive dataset of 2,843 videos from eight countries, including 1,359 misleading thumbnail videos that collectively amassed over 7.6 billion views -- providing a unique cross-cultural perspective on this global issue. Our detection pipeline integrates video-to-text descriptions, thumbnail images, and subtitle transcr"},"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":"2509.04714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2025-09-05T00:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"260eb63a5f3df9dcedda972e69f06f7964b920a641794e49357b3219f19e6196","abstract_canon_sha256":"5983bb021a3ca20d49d7d9c7e07d81e0f0fde9213db03ef3c1a48a8f3840b2b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:28.267958Z","signature_b64":"aqm5WELfztodTkq6oAIVsbDnXAn2dnomn/ejEGnMZfHhu6urshkJmvufGA5vLEWmKhJV5vUFOiDgrhmKkY2hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1a8e24884b0c0aeb3d4046e5d22381b511402dcd32333cd330243b3a53a0b1","last_reissued_at":"2026-07-05T12:05:28.267502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:28.267502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Wajiha Naveed, Zafar Ayyub Qazi, Zartash Afzal Uzmi","submitted_at":"2025-09-05T00:02:17Z","abstract_excerpt":"Misleading video thumbnails on platforms like YouTube are a pervasive problem, undermining user trust and platform integrity. This paper proposes a novel multi-modal detection pipeline that uses Large Language Models (LLMs) to flag misleading thumbnails. We first construct a comprehensive dataset of 2,843 videos from eight countries, including 1,359 misleading thumbnail videos that collectively amassed over 7.6 billion views -- providing a unique cross-cultural perspective on this global issue. Our detection pipeline integrates video-to-text descriptions, thumbnail images, and subtitle transcr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04714","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/2509.04714/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":"2509.04714","created_at":"2026-07-05T12:05:28.267575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04714v1","created_at":"2026-07-05T12:05:28.267575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04714","created_at":"2026-07-05T12:05:28.267575+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQNI4JEIJMGA","created_at":"2026-07-05T12:05:28.267575+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQNI4JEIJMGAV2Z5","created_at":"2026-07-05T12:05:28.267575+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQNI4JEI","created_at":"2026-07-05T12:05:28.267575+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/RQNI4JEIJMGAV2Z5IBDOLURDQG","json":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG.json","graph_json":"https://pith.science/api/pith-number/RQNI4JEIJMGAV2Z5IBDOLURDQG/graph.json","events_json":"https://pith.science/api/pith-number/RQNI4JEIJMGAV2Z5IBDOLURDQG/events.json","paper":"https://pith.science/paper/RQNI4JEI"},"agent_actions":{"view_html":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG","download_json":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG.json","view_paper":"https://pith.science/paper/RQNI4JEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04714&json=true","fetch_graph":"https://pith.science/api/pith-number/RQNI4JEIJMGAV2Z5IBDOLURDQG/graph.json","fetch_events":"https://pith.science/api/pith-number/RQNI4JEIJMGAV2Z5IBDOLURDQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG/action/storage_attestation","attest_author":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG/action/author_attestation","sign_citation":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG/action/citation_signature","submit_replication":"https://pith.science/pith/RQNI4JEIJMGAV2Z5IBDOLURDQG/action/replication_record"}},"created_at":"2026-07-05T12:05:28.267575+00:00","updated_at":"2026-07-05T12:05:28.267575+00:00"}