{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RVCWJSXURHB3YUVJFDW6P4ZR7M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f36276f749655231f1691fd7806fd816c1552e63491e9e7b7aff768cb734e245","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T10:51:46Z","title_canon_sha256":"91bb4e711679ffbe2fe77026ec056639642f3e2829fa33563de14769da902d94"},"schema_version":"1.0","source":{"id":"2407.17152","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17152","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17152v4","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17152","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"RVCWJSXURHB3","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_16","alias_value":"RVCWJSXURHB3YUVJ","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_8","alias_value":"RVCWJSXU","created_at":"2026-07-05T11:19:49Z"}],"graph_snapshots":[{"event_id":"sha256:9419d70333be29609afa3763c7c787b21468b46a51cd72416b022bb67567a883","target":"graph","created_at":"2026-07-05T11:19:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.17152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines. While advances have been made in natural language processing, real-world humor often thrives in a multi-modal context, encapsulated distinctively by memes. This paper poses a particular emphasis on the impact of multi-images on meme captioning. After that, we introduce the \\textsc{XMeCap} framework, a novel approach that adopts supervised fine-tuning and reinforcement learning based on an innovative reward model, which factors in both global and local similarities between visuals and text. Ou","authors_text":"Songzhou Yan, Yanghua Xiao, Yuyan Chen, Zhihong Zhu, Zhixu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T10:51:46Z","title":"XMeCap: Meme Caption Generation with Sub-Image Adaptability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17152","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b8c607f327f26edac3c7bbf5046c9ef3c1f229a50c181d1393825b6ce4a65f3","target":"record","created_at":"2026-07-05T11:19:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f36276f749655231f1691fd7806fd816c1552e63491e9e7b7aff768cb734e245","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T10:51:46Z","title_canon_sha256":"91bb4e711679ffbe2fe77026ec056639642f3e2829fa33563de14769da902d94"},"schema_version":"1.0","source":{"id":"2407.17152","kind":"arxiv","version":4}},"canonical_sha256":"8d4564caf489c3bc52a928ede7f331fb0cf8b79fc0e05057e72bc229d15c29dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d4564caf489c3bc52a928ede7f331fb0cf8b79fc0e05057e72bc229d15c29dd","first_computed_at":"2026-07-05T11:19:49.145753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:49.145753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdrkp6095aAfxm6913bPB3j0LTRpKYqhvqRSCtKe4wKsBw1K3w2pmvwxAs84eRIIsDB7uruUQ6BI0tF7cJ4yCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:49.146217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17152","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b8c607f327f26edac3c7bbf5046c9ef3c1f229a50c181d1393825b6ce4a65f3","sha256:9419d70333be29609afa3763c7c787b21468b46a51cd72416b022bb67567a883"],"state_sha256":"89cabe6f56e4c85711c966156732a94ac9ae7ae3e412d08000993e2940dbf6e8"}