{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DSBE3Q3OBM7IO73CABR77APDTI","short_pith_number":"pith:DSBE3Q3O","schema_version":"1.0","canonical_sha256":"1c824dc36e0b3e877f620063ff81e39a078faed5ecdb239f38b433649884020f","source":{"kind":"arxiv","id":"2210.05916","version":3},"attestation_state":"computed","paper":{"title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Gokul Karthik Kumar, Karthik Nandakumar","submitted_at":"2022-10-12T04:34:54Z","abstract_excerpt":"Hateful memes are a growing menace on social media. While the image and its corresponding text in a meme are related, they do not necessarily convey the same meaning when viewed individually. Hence, detecting hateful memes requires careful consideration of both visual and textual information. Multimodal pre-training can be beneficial for this task because it effectively captures the relationship between the image and the text by representing them in a similar feature space. Furthermore, it is essential to model the interactions between the image and text features through intermediate fusion. M"},"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":"2210.05916","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T04:34:54Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"056e638b08b9c0a94e4e34a8da1c1189ebf635702ce8ca48a60251c58d009e07","abstract_canon_sha256":"726ea521f084d4b36601059ceeff3d527d4c6bf787ac49447af20d1fbdb7140c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:05.070899Z","signature_b64":"Y+Nkkj1jBYmQdUPzTsuDiJ+gqEDWZg8YfC7cVbUAbD5lcJdCopbeHbfbLlnYyl/eDxhLnblUWoTcpiraltBECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c824dc36e0b3e877f620063ff81e39a078faed5ecdb239f38b433649884020f","last_reissued_at":"2026-07-05T05:07:05.070461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:05.070461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Gokul Karthik Kumar, Karthik Nandakumar","submitted_at":"2022-10-12T04:34:54Z","abstract_excerpt":"Hateful memes are a growing menace on social media. While the image and its corresponding text in a meme are related, they do not necessarily convey the same meaning when viewed individually. Hence, detecting hateful memes requires careful consideration of both visual and textual information. Multimodal pre-training can be beneficial for this task because it effectively captures the relationship between the image and the text by representing them in a similar feature space. Furthermore, it is essential to model the interactions between the image and text features through intermediate fusion. M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05916","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/2210.05916/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":"2210.05916","created_at":"2026-07-05T05:07:05.070526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05916v3","created_at":"2026-07-05T05:07:05.070526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05916","created_at":"2026-07-05T05:07:05.070526+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSBE3Q3OBM7I","created_at":"2026-07-05T05:07:05.070526+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSBE3Q3OBM7IO73C","created_at":"2026-07-05T05:07:05.070526+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSBE3Q3O","created_at":"2026-07-05T05:07:05.070526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI","json":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI.json","graph_json":"https://pith.science/api/pith-number/DSBE3Q3OBM7IO73CABR77APDTI/graph.json","events_json":"https://pith.science/api/pith-number/DSBE3Q3OBM7IO73CABR77APDTI/events.json","paper":"https://pith.science/paper/DSBE3Q3O"},"agent_actions":{"view_html":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI","download_json":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI.json","view_paper":"https://pith.science/paper/DSBE3Q3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05916&json=true","fetch_graph":"https://pith.science/api/pith-number/DSBE3Q3OBM7IO73CABR77APDTI/graph.json","fetch_events":"https://pith.science/api/pith-number/DSBE3Q3OBM7IO73CABR77APDTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI/action/storage_attestation","attest_author":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI/action/author_attestation","sign_citation":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI/action/citation_signature","submit_replication":"https://pith.science/pith/DSBE3Q3OBM7IO73CABR77APDTI/action/replication_record"}},"created_at":"2026-07-05T05:07:05.070526+00:00","updated_at":"2026-07-05T05:07:05.070526+00:00"}