{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GRUUKDDVAFJNKB7WBZXPAWQEBB","short_pith_number":"pith:GRUUKDDV","schema_version":"1.0","canonical_sha256":"3469450c750152d507f60e6ef05a04087045b3e0009d6f9b2a440d55c38e043a","source":{"kind":"arxiv","id":"2411.05383","version":1},"attestation_state":"computed","paper":{"title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guang Chen, Hongzhan Lin, Jianzhao Huang, Jing Ma, Ziyang Luo, Ziyan Liu","submitted_at":"2024-11-08T07:43:15Z","abstract_excerpt":"The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled examples are available. In this paper, we propose an agency-driven framework for low-resource harmful meme detection, employing both outward and inward analysis with few-shot annotated samples. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first retrieve relative memes with annotations to leverage label"},"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":"2411.05383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T07:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"6305f29df3477a2daee2c4edb48fd75186634e29c893246e018dca5747664b43","abstract_canon_sha256":"1f58c55ae80f4439e9184b67ec8ea4f4377b021b205de70a69403054573c0c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:59.717688Z","signature_b64":"0tLaTEmA4GOOH6sS+N0eNRoeGH1OGohZoJPNijPSGZSFF4DOi/RuKjCaghI2E7dkN274kgrXMV0qUQ/ROPhPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3469450c750152d507f60e6ef05a04087045b3e0009d6f9b2a440d55c38e043a","last_reissued_at":"2026-07-05T09:32:59.717188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:59.717188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guang Chen, Hongzhan Lin, Jianzhao Huang, Jing Ma, Ziyang Luo, Ziyan Liu","submitted_at":"2024-11-08T07:43:15Z","abstract_excerpt":"The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled examples are available. In this paper, we propose an agency-driven framework for low-resource harmful meme detection, employing both outward and inward analysis with few-shot annotated samples. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first retrieve relative memes with annotations to leverage label"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05383","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/2411.05383/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":"2411.05383","created_at":"2026-07-05T09:32:59.717252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05383v1","created_at":"2026-07-05T09:32:59.717252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05383","created_at":"2026-07-05T09:32:59.717252+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRUUKDDVAFJN","created_at":"2026-07-05T09:32:59.717252+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRUUKDDVAFJNKB7W","created_at":"2026-07-05T09:32:59.717252+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRUUKDDV","created_at":"2026-07-05T09:32:59.717252+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/GRUUKDDVAFJNKB7WBZXPAWQEBB","json":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB.json","graph_json":"https://pith.science/api/pith-number/GRUUKDDVAFJNKB7WBZXPAWQEBB/graph.json","events_json":"https://pith.science/api/pith-number/GRUUKDDVAFJNKB7WBZXPAWQEBB/events.json","paper":"https://pith.science/paper/GRUUKDDV"},"agent_actions":{"view_html":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB","download_json":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB.json","view_paper":"https://pith.science/paper/GRUUKDDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05383&json=true","fetch_graph":"https://pith.science/api/pith-number/GRUUKDDVAFJNKB7WBZXPAWQEBB/graph.json","fetch_events":"https://pith.science/api/pith-number/GRUUKDDVAFJNKB7WBZXPAWQEBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB/action/storage_attestation","attest_author":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB/action/author_attestation","sign_citation":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB/action/citation_signature","submit_replication":"https://pith.science/pith/GRUUKDDVAFJNKB7WBZXPAWQEBB/action/replication_record"}},"created_at":"2026-07-05T09:32:59.717252+00:00","updated_at":"2026-07-05T09:32:59.717252+00:00"}