{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YCLLSCYDLIDDCSPWYX4WOLVAY2","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":"a208a980890c1ce23d72185eb7930ac33c37959dc90a2dcac1ee49053afd4d44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:11:45Z","title_canon_sha256":"1c496532eb4e71d416d459bbf608b06b54a6c0298640d347380422446d1ec502"},"schema_version":"1.0","source":{"id":"2403.03719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03719","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03719v1","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03719","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"YCLLSCYDLIDD","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_16","alias_value":"YCLLSCYDLIDDCSPW","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_8","alias_value":"YCLLSCYD","created_at":"2026-07-05T07:52:52Z"}],"graph_snapshots":[{"event_id":"sha256:8e97fbdfa889e09a8cb5b319c088dbba046550842def15883cd49ef71c4f538d","target":"graph","created_at":"2026-07-05T07:52:52Z","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/2403.03719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work explores a closure task in comics, a medium where visual and textual elements are intricately intertwined. Specifically, Text-cloze refers to the task of selecting the correct text to use in a comic panel, given its neighboring panels. Traditional methods based on recurrent neural networks have struggled with this task due to limited OCR accuracy and inherent model limitations. We introduce a novel Multimodal Large Language Model (Multimodal-LLM) architecture, specifically designed for Text-cloze, achieving a 10% improvement over existing state-of-the-art models in both its easy and ","authors_text":"Dimosthenis Karatzas, Emanuele Vivoli, Ernest Valveny Llobet, Joan Lafuente Baeza","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:11:45Z","title":"Multimodal Transformer for Comics Text-Cloze"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03719","kind":"arxiv","version":1},"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":"sha256:8ade0642f4d3f8255392fc55afded67b1a26389d8edc5d21b79ad5bb6398d0f2","target":"record","created_at":"2026-07-05T07:52:52Z","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":"a208a980890c1ce23d72185eb7930ac33c37959dc90a2dcac1ee49053afd4d44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:11:45Z","title_canon_sha256":"1c496532eb4e71d416d459bbf608b06b54a6c0298640d347380422446d1ec502"},"schema_version":"1.0","source":{"id":"2403.03719","kind":"arxiv","version":1}},"canonical_sha256":"c096b90b035a063149f6c5f9672ea0c6abd7f712358e8869e1c8f04ee104ce70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c096b90b035a063149f6c5f9672ea0c6abd7f712358e8869e1c8f04ee104ce70","first_computed_at":"2026-07-05T07:52:52.110194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:52.110194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mgSV5IhQ938XJEIEWPpYrYs395P9aWVpkqgG9BsWd9qlRJkNQw95MJJthhAMlR5xWNgSCGVIAp40KDdJeqI3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:52.110634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ade0642f4d3f8255392fc55afded67b1a26389d8edc5d21b79ad5bb6398d0f2","sha256:8e97fbdfa889e09a8cb5b319c088dbba046550842def15883cd49ef71c4f538d"],"state_sha256":"84c50dc58fdd30934fab6b12875beadfc86501bc583de8ccc92f1e43849a7657"}