{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MLBHFKFYCU4M4D6ABXHBYXZQ5D","short_pith_number":"pith:MLBHFKFY","schema_version":"1.0","canonical_sha256":"62c272a8b81538ce0fc00dce1c5f30e8f4e8b2f733828730322f6d9ddbc59f28","source":{"kind":"arxiv","id":"2012.12871","version":2},"attestation_state":"computed","paper":{"title":"A Multimodal Framework for the Detection of Hateful Memes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Shutova, Georgios Antoniou, Helen Yannakoudakis, Nithin Holla, Phillip Lippe, Santhosh Rajamanickam, Shantanu Chandra","submitted_at":"2020-12-23T18:37:11Z","abstract_excerpt":"An increasingly common expression of online hate speech is multimodal in nature and comes in the form of memes. Designing systems to automatically detect hateful content is of paramount importance if we are to mitigate its undesirable effects on the society at large. The detection of multimodal hate speech is an intrinsically difficult and open problem: memes convey a message using both images and text and, hence, require multimodal reasoning and joint visual and language understanding. In this work, we seek to advance this line of research and develop a multimodal framework for the detection "},"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":"2012.12871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-23T18:37:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e4421f38995d3dd2aeb03fb760d94a78153d85c60d52551f0fbed96fe24b4f6","abstract_canon_sha256":"0d169d63f8e87f36e232683ef78ffa1c21cafd9f1966d365a77c2a3f74dbd096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:16.488551Z","signature_b64":"W8BVu4l+JGpX+/uEaf4Y3I36qgkgBgXIHwv8KVL+pmmFYfIKhVVfV/GNeNRXZCdZh0Ji20hEENBf9XFlaxiAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c272a8b81538ce0fc00dce1c5f30e8f4e8b2f733828730322f6d9ddbc59f28","last_reissued_at":"2026-07-05T03:06:16.488119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:16.488119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multimodal Framework for the Detection of Hateful Memes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Shutova, Georgios Antoniou, Helen Yannakoudakis, Nithin Holla, Phillip Lippe, Santhosh Rajamanickam, Shantanu Chandra","submitted_at":"2020-12-23T18:37:11Z","abstract_excerpt":"An increasingly common expression of online hate speech is multimodal in nature and comes in the form of memes. Designing systems to automatically detect hateful content is of paramount importance if we are to mitigate its undesirable effects on the society at large. The detection of multimodal hate speech is an intrinsically difficult and open problem: memes convey a message using both images and text and, hence, require multimodal reasoning and joint visual and language understanding. In this work, we seek to advance this line of research and develop a multimodal framework for the detection "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12871","kind":"arxiv","version":2},"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/2012.12871/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":"2012.12871","created_at":"2026-07-05T03:06:16.488181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12871v2","created_at":"2026-07-05T03:06:16.488181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12871","created_at":"2026-07-05T03:06:16.488181+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLBHFKFYCU4M","created_at":"2026-07-05T03:06:16.488181+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLBHFKFYCU4M4D6A","created_at":"2026-07-05T03:06:16.488181+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLBHFKFY","created_at":"2026-07-05T03:06:16.488181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.07353","citing_title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15946","citing_title":"Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D","json":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D.json","graph_json":"https://pith.science/api/pith-number/MLBHFKFYCU4M4D6ABXHBYXZQ5D/graph.json","events_json":"https://pith.science/api/pith-number/MLBHFKFYCU4M4D6ABXHBYXZQ5D/events.json","paper":"https://pith.science/paper/MLBHFKFY"},"agent_actions":{"view_html":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D","download_json":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D.json","view_paper":"https://pith.science/paper/MLBHFKFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12871&json=true","fetch_graph":"https://pith.science/api/pith-number/MLBHFKFYCU4M4D6ABXHBYXZQ5D/graph.json","fetch_events":"https://pith.science/api/pith-number/MLBHFKFYCU4M4D6ABXHBYXZQ5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D/action/storage_attestation","attest_author":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D/action/author_attestation","sign_citation":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D/action/citation_signature","submit_replication":"https://pith.science/pith/MLBHFKFYCU4M4D6ABXHBYXZQ5D/action/replication_record"}},"created_at":"2026-07-05T03:06:16.488181+00:00","updated_at":"2026-07-05T03:06:16.488181+00:00"}