{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DPTNCCMGGRYUGRAZITHMNK453X","short_pith_number":"pith:DPTNCCMG","schema_version":"1.0","canonical_sha256":"1be6d10986347143441944cec6ab9dddc0f706368fdee40d2e09862d4eeacfc3","source":{"kind":"arxiv","id":"2005.04790","version":3},"attestation_state":"computed","paper":{"title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Amanpreet Singh, Aravind Mohan, Davide Testuggine, Douwe Kiela, Hamed Firooz, Pratik Ringshia, Vedanuj Goswami","submitted_at":"2020-05-10T21:31:00Z","abstract_excerpt":"This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples (\"benign confounders\") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art"},"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":"2005.04790","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-05-10T21:31:00Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"42acaf500c144e76a2a4ae147fffeb096b76d641a58cebfee685983e9feccce9","abstract_canon_sha256":"26531f9e8d2510dadabf561159791d5e93f7c1fb626ddaa065c52627b8453568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:12.286380Z","signature_b64":"SyOFdlLxcXxN5qQj8lm1+S3YHw0W43lYZZ9PJtJRr9UHmLHkWsWQ/LMFUnaDAi9KRgnETleg5xPHxCUxP+JWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be6d10986347143441944cec6ab9dddc0f706368fdee40d2e09862d4eeacfc3","last_reissued_at":"2026-07-05T02:30:12.285841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:12.285841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Amanpreet Singh, Aravind Mohan, Davide Testuggine, Douwe Kiela, Hamed Firooz, Pratik Ringshia, Vedanuj Goswami","submitted_at":"2020-05-10T21:31:00Z","abstract_excerpt":"This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples (\"benign confounders\") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04790","kind":"arxiv","version":3},"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/2005.04790/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":"2005.04790","created_at":"2026-07-05T02:30:12.285912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04790v3","created_at":"2026-07-05T02:30:12.285912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04790","created_at":"2026-07-05T02:30:12.285912+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPTNCCMGGRYU","created_at":"2026-07-05T02:30:12.285912+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPTNCCMGGRYUGRAZ","created_at":"2026-07-05T02:30:12.285912+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPTNCCMG","created_at":"2026-07-05T02:30:12.285912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01831","citing_title":"Routing-Based Continual Learning for Multimodal Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X","json":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X.json","graph_json":"https://pith.science/api/pith-number/DPTNCCMGGRYUGRAZITHMNK453X/graph.json","events_json":"https://pith.science/api/pith-number/DPTNCCMGGRYUGRAZITHMNK453X/events.json","paper":"https://pith.science/paper/DPTNCCMG"},"agent_actions":{"view_html":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X","download_json":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X.json","view_paper":"https://pith.science/paper/DPTNCCMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04790&json=true","fetch_graph":"https://pith.science/api/pith-number/DPTNCCMGGRYUGRAZITHMNK453X/graph.json","fetch_events":"https://pith.science/api/pith-number/DPTNCCMGGRYUGRAZITHMNK453X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X/action/storage_attestation","attest_author":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X/action/author_attestation","sign_citation":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X/action/citation_signature","submit_replication":"https://pith.science/pith/DPTNCCMGGRYUGRAZITHMNK453X/action/replication_record"}},"created_at":"2026-07-05T02:30:12.285912+00:00","updated_at":"2026-07-05T02:30:12.285912+00:00"}