{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PH3U6CFFAGURR5BHEXDSN22NBB","short_pith_number":"pith:PH3U6CFF","schema_version":"1.0","canonical_sha256":"79f74f08a501a918f42725c726eb4d0866c9867f6d399f847ff047060279f9b0","source":{"kind":"arxiv","id":"2607.22016","version":1},"attestation_state":"computed","paper":{"title":"EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","submitted_at":"2026-07-24T06:28:57Z","abstract_excerpt":"MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a joint interpretation of text and vision. Existing methods focus on the dual-stream vision-language model to extract the visual and text simultaneously, which lacks background information and prior knowledge about the comprehensive explanation of MEME. One feasible option is to adopt chain-of-thought (CoT). However, the simple CoT approach lacks multi-perspective thinking, which may compromise the reliability of the resulting answers. Moreover, it o"},"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":"2607.22016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:28:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5cd3cc20d9d1c5aed005154ecf10d5a484e68eea7b2a40a9fbdb5ad73ff32fd","abstract_canon_sha256":"49acd951b2380abbd12a94029f4fc51b3d872d9821693c56d78f2ff41b238eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:43.342645Z","signature_b64":"fAZYbRpWszxEpdB72boFVCbzPMAprfS1qVqrdqVxdvgY1Llf+44dwCrK8kjQsaChUphw4Z7SqF+ee9KfTwGnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f74f08a501a918f42725c726eb4d0866c9867f6d399f847ff047060279f9b0","last_reissued_at":"2026-07-27T01:20:43.341837Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:43.341837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","submitted_at":"2026-07-24T06:28:57Z","abstract_excerpt":"MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a joint interpretation of text and vision. Existing methods focus on the dual-stream vision-language model to extract the visual and text simultaneously, which lacks background information and prior knowledge about the comprehensive explanation of MEME. One feasible option is to adopt chain-of-thought (CoT). However, the simple CoT approach lacks multi-perspective thinking, which may compromise the reliability of the resulting answers. Moreover, it o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22016","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/2607.22016/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":"2607.22016","created_at":"2026-07-27T01:20:43.342254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22016v1","created_at":"2026-07-27T01:20:43.342254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22016","created_at":"2026-07-27T01:20:43.342254+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH3U6CFFAGUR","created_at":"2026-07-27T01:20:43.342254+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH3U6CFFAGURR5BH","created_at":"2026-07-27T01:20:43.342254+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH3U6CFF","created_at":"2026-07-27T01:20:43.342254+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/PH3U6CFFAGURR5BHEXDSN22NBB","json":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB.json","graph_json":"https://pith.science/api/pith-number/PH3U6CFFAGURR5BHEXDSN22NBB/graph.json","events_json":"https://pith.science/api/pith-number/PH3U6CFFAGURR5BHEXDSN22NBB/events.json","paper":"https://pith.science/paper/PH3U6CFF"},"agent_actions":{"view_html":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB","download_json":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB.json","view_paper":"https://pith.science/paper/PH3U6CFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22016&json=true","fetch_graph":"https://pith.science/api/pith-number/PH3U6CFFAGURR5BHEXDSN22NBB/graph.json","fetch_events":"https://pith.science/api/pith-number/PH3U6CFFAGURR5BHEXDSN22NBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB/action/storage_attestation","attest_author":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB/action/author_attestation","sign_citation":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB/action/citation_signature","submit_replication":"https://pith.science/pith/PH3U6CFFAGURR5BHEXDSN22NBB/action/replication_record"}},"created_at":"2026-07-27T01:20:43.342254+00:00","updated_at":"2026-07-27T01:20:43.342254+00:00"}