{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YCLLSCYDLIDDCSPWYX4WOLVAY2","short_pith_number":"pith:YCLLSCYD","schema_version":"1.0","canonical_sha256":"c096b90b035a063149f6c5f9672ea0c6abd7f712358e8869e1c8f04ee104ce70","source":{"kind":"arxiv","id":"2403.03719","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Transformer for Comics Text-Cloze","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimosthenis Karatzas, Emanuele Vivoli, Ernest Valveny Llobet, Joan Lafuente Baeza","submitted_at":"2024-03-06T14:11:45Z","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 "},"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":"2403.03719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:11:45Z","cross_cats_sorted":[],"title_canon_sha256":"1c496532eb4e71d416d459bbf608b06b54a6c0298640d347380422446d1ec502","abstract_canon_sha256":"a208a980890c1ce23d72185eb7930ac33c37959dc90a2dcac1ee49053afd4d44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:52.110634Z","signature_b64":"mgSV5IhQ938XJEIEWPpYrYs395P9aWVpkqgG9BsWd9qlRJkNQw95MJJthhAMlR5xWNgSCGVIAp40KDdJeqI3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c096b90b035a063149f6c5f9672ea0c6abd7f712358e8869e1c8f04ee104ce70","last_reissued_at":"2026-07-05T07:52:52.110194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:52.110194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Transformer for Comics Text-Cloze","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimosthenis Karatzas, Emanuele Vivoli, Ernest Valveny Llobet, Joan Lafuente Baeza","submitted_at":"2024-03-06T14:11:45Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03719","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/2403.03719/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":"2403.03719","created_at":"2026-07-05T07:52:52.110251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03719v1","created_at":"2026-07-05T07:52:52.110251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03719","created_at":"2026-07-05T07:52:52.110251+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCLLSCYDLIDD","created_at":"2026-07-05T07:52:52.110251+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCLLSCYDLIDDCSPW","created_at":"2026-07-05T07:52:52.110251+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCLLSCYD","created_at":"2026-07-05T07:52:52.110251+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/YCLLSCYDLIDDCSPWYX4WOLVAY2","json":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2.json","graph_json":"https://pith.science/api/pith-number/YCLLSCYDLIDDCSPWYX4WOLVAY2/graph.json","events_json":"https://pith.science/api/pith-number/YCLLSCYDLIDDCSPWYX4WOLVAY2/events.json","paper":"https://pith.science/paper/YCLLSCYD"},"agent_actions":{"view_html":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2","download_json":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2.json","view_paper":"https://pith.science/paper/YCLLSCYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03719&json=true","fetch_graph":"https://pith.science/api/pith-number/YCLLSCYDLIDDCSPWYX4WOLVAY2/graph.json","fetch_events":"https://pith.science/api/pith-number/YCLLSCYDLIDDCSPWYX4WOLVAY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2/action/storage_attestation","attest_author":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2/action/author_attestation","sign_citation":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2/action/citation_signature","submit_replication":"https://pith.science/pith/YCLLSCYDLIDDCSPWYX4WOLVAY2/action/replication_record"}},"created_at":"2026-07-05T07:52:52.110251+00:00","updated_at":"2026-07-05T07:52:52.110251+00:00"}