{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7YAFU5VM6UQTWMGV6LRHIL6FX","short_pith_number":"pith:J7YAFU5V","schema_version":"1.0","canonical_sha256":"4ff002d3b567a909d986af9713a17e2de7b5b1ef42ad742fa1cc721dd8ad8168","source":{"kind":"arxiv","id":"2504.19267","version":3},"attestation_state":"computed","paper":{"title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dmitry Ignatov, Mohamed Gado, Muhammad Memon, Radu Timofte, Towhid Taliee","submitted_at":"2025-04-27T14:55:51Z","abstract_excerpt":"Visual storytelling is an interdisciplinary field combining computer vision and natural language processing to generate cohesive narratives from sequences of images. This paper presents a novel approach that leverages recent advancements in multimodal models, specifically adapting transformer-based architectures and large multimodal models, for the visual storytelling task. Leveraging the large-scale Visual Storytelling (VIST) dataset, our VIST-GPT model produces visually grounded, contextually appropriate narratives. We address the limitations of traditional evaluation metrics, such as BLEU, "},"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":"2504.19267","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T14:55:51Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"5326239cd61a56e65ff213581834427b5587ed86aaf1794ecdd287a852f20d47","abstract_canon_sha256":"69805f91602d35f8ee5b266cf72d67445f928e663e662060fba62c0993d746c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:06.552020Z","signature_b64":"jpkrhUvUxWwkB2DhG1QOU30fzCcbK/lZbJbPH9C5t0GKLzoKosSO8hOdrf/JiyNKF+I0zzXFZzPexeBv3j3dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff002d3b567a909d986af9713a17e2de7b5b1ef42ad742fa1cc721dd8ad8168","last_reissued_at":"2026-07-05T11:19:06.551556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:06.551556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dmitry Ignatov, Mohamed Gado, Muhammad Memon, Radu Timofte, Towhid Taliee","submitted_at":"2025-04-27T14:55:51Z","abstract_excerpt":"Visual storytelling is an interdisciplinary field combining computer vision and natural language processing to generate cohesive narratives from sequences of images. This paper presents a novel approach that leverages recent advancements in multimodal models, specifically adapting transformer-based architectures and large multimodal models, for the visual storytelling task. Leveraging the large-scale Visual Storytelling (VIST) dataset, our VIST-GPT model produces visually grounded, contextually appropriate narratives. We address the limitations of traditional evaluation metrics, such as BLEU, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19267","kind":"arxiv","version":3},"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/2504.19267/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":"2504.19267","created_at":"2026-07-05T11:19:06.551610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19267v3","created_at":"2026-07-05T11:19:06.551610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19267","created_at":"2026-07-05T11:19:06.551610+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7YAFU5VM6UQ","created_at":"2026-07-05T11:19:06.551610+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7YAFU5VM6UQTWMG","created_at":"2026-07-05T11:19:06.551610+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7YAFU5V","created_at":"2026-07-05T11:19:06.551610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06839","citing_title":"LEMUR 2: Unlocking Neural Network Diversity for AI","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00009","citing_title":"Controllable Narrative Rendering for Enhanced Assisted Writing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07329","citing_title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07329","citing_title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24120","citing_title":"Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08517","citing_title":"Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04903","citing_title":"Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX","json":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX.json","graph_json":"https://pith.science/api/pith-number/J7YAFU5VM6UQTWMGV6LRHIL6FX/graph.json","events_json":"https://pith.science/api/pith-number/J7YAFU5VM6UQTWMGV6LRHIL6FX/events.json","paper":"https://pith.science/paper/J7YAFU5V"},"agent_actions":{"view_html":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX","download_json":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX.json","view_paper":"https://pith.science/paper/J7YAFU5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19267&json=true","fetch_graph":"https://pith.science/api/pith-number/J7YAFU5VM6UQTWMGV6LRHIL6FX/graph.json","fetch_events":"https://pith.science/api/pith-number/J7YAFU5VM6UQTWMGV6LRHIL6FX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX/action/storage_attestation","attest_author":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX/action/author_attestation","sign_citation":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX/action/citation_signature","submit_replication":"https://pith.science/pith/J7YAFU5VM6UQTWMGV6LRHIL6FX/action/replication_record"}},"created_at":"2026-07-05T11:19:06.551610+00:00","updated_at":"2026-07-05T11:19:06.551610+00:00"}