{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DBFVMFMMQND5VQEGXUXWK3Y2RH","short_pith_number":"pith:DBFVMFMM","schema_version":"1.0","canonical_sha256":"184b56158c8347dac086bd2f656f1a89f718ea405a75e0eb16a1254d3bcfbb5e","source":{"kind":"arxiv","id":"2311.06737","version":1},"attestation_state":"computed","paper":{"title":"Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Minh-Hao Van, Xintao Wu","submitted_at":"2023-11-12T05:20:20Z","abstract_excerpt":"Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore more emergent abilities in multimodality. Visual language models (VLMs), such as LLaVA, Flamingo, or GPT-4, have demonstrated impressive performance on various visio-linguistic tasks. Consequently, there are enormous applications of large models that could be potentially used on social media platforms. Despite that, there is a lack of related work on detecting or correcting hateful memes with VLMs. In this work, we study the ability "},"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":"2311.06737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T05:20:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b600e0b284d27d68d13591ce5cac0d84ad744856235876f83ed2d02a2ebb257","abstract_canon_sha256":"0ed8385fa45a6c70c4ec80783898b247f3aeb32c38d142441cfd6f9f1d651a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:02.715260Z","signature_b64":"eytQY1/Nv+Nc/YJFSR8g7Deac6USueySBsDyl+Q2KBYxV7kBn+8wWpzO5VaMKpCa565DBSx3IFrKZKoSQ4bZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184b56158c8347dac086bd2f656f1a89f718ea405a75e0eb16a1254d3bcfbb5e","last_reissued_at":"2026-07-05T07:12:02.714775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:02.714775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Minh-Hao Van, Xintao Wu","submitted_at":"2023-11-12T05:20:20Z","abstract_excerpt":"Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore more emergent abilities in multimodality. Visual language models (VLMs), such as LLaVA, Flamingo, or GPT-4, have demonstrated impressive performance on various visio-linguistic tasks. Consequently, there are enormous applications of large models that could be potentially used on social media platforms. Despite that, there is a lack of related work on detecting or correcting hateful memes with VLMs. In this work, we study the ability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06737","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/2311.06737/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":"2311.06737","created_at":"2026-07-05T07:12:02.714833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06737v1","created_at":"2026-07-05T07:12:02.714833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06737","created_at":"2026-07-05T07:12:02.714833+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBFVMFMMQND5","created_at":"2026-07-05T07:12:02.714833+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBFVMFMMQND5VQEG","created_at":"2026-07-05T07:12:02.714833+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBFVMFMM","created_at":"2026-07-05T07:12:02.714833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH","json":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH.json","graph_json":"https://pith.science/api/pith-number/DBFVMFMMQND5VQEGXUXWK3Y2RH/graph.json","events_json":"https://pith.science/api/pith-number/DBFVMFMMQND5VQEGXUXWK3Y2RH/events.json","paper":"https://pith.science/paper/DBFVMFMM"},"agent_actions":{"view_html":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH","download_json":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH.json","view_paper":"https://pith.science/paper/DBFVMFMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06737&json=true","fetch_graph":"https://pith.science/api/pith-number/DBFVMFMMQND5VQEGXUXWK3Y2RH/graph.json","fetch_events":"https://pith.science/api/pith-number/DBFVMFMMQND5VQEGXUXWK3Y2RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH/action/storage_attestation","attest_author":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH/action/author_attestation","sign_citation":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH/action/citation_signature","submit_replication":"https://pith.science/pith/DBFVMFMMQND5VQEGXUXWK3Y2RH/action/replication_record"}},"created_at":"2026-07-05T07:12:02.714833+00:00","updated_at":"2026-07-05T07:12:02.714833+00:00"}