{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7YAFU5VM6UQTWMGV6LRHIL6FX","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":"69805f91602d35f8ee5b266cf72d67445f928e663e662060fba62c0993d746c6","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T14:55:51Z","title_canon_sha256":"5326239cd61a56e65ff213581834427b5587ed86aaf1794ecdd287a852f20d47"},"schema_version":"1.0","source":{"id":"2504.19267","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19267","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19267v3","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19267","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"J7YAFU5VM6UQ","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"J7YAFU5VM6UQTWMG","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"J7YAFU5V","created_at":"2026-07-05T11:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:56463971a7679f6f555166da802d243297331686766b14029a106cb6e9a2fab7","target":"graph","created_at":"2026-07-05T11:19:06Z","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/2504.19267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Dmitry Ignatov, Mohamed Gado, Muhammad Memon, Radu Timofte, Towhid Taliee","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T14:55:51Z","title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19267","kind":"arxiv","version":3},"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":"sha256:6d73b8135faad61a5e759dbf8c8b2d107c012ad00eb27db97297dd78a68c0dd6","target":"record","created_at":"2026-07-05T11:19:06Z","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":"69805f91602d35f8ee5b266cf72d67445f928e663e662060fba62c0993d746c6","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T14:55:51Z","title_canon_sha256":"5326239cd61a56e65ff213581834427b5587ed86aaf1794ecdd287a852f20d47"},"schema_version":"1.0","source":{"id":"2504.19267","kind":"arxiv","version":3}},"canonical_sha256":"4ff002d3b567a909d986af9713a17e2de7b5b1ef42ad742fa1cc721dd8ad8168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ff002d3b567a909d986af9713a17e2de7b5b1ef42ad742fa1cc721dd8ad8168","first_computed_at":"2026-07-05T11:19:06.551556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:06.551556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jpkrhUvUxWwkB2DhG1QOU30fzCcbK/lZbJbPH9C5t0GKLzoKosSO8hOdrf/JiyNKF+I0zzXFZzPexeBv3j3dCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:06.552020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19267","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d73b8135faad61a5e759dbf8c8b2d107c012ad00eb27db97297dd78a68c0dd6","sha256:56463971a7679f6f555166da802d243297331686766b14029a106cb6e9a2fab7"],"state_sha256":"908a6bd94a354372d03f02b33cc9447e96afe2c83401b6be54ed09a8ab437c1c"}