{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZNRXALNNK36A6GTTNNARZ6OLMJ","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":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a"},"schema_version":"1.0","source":{"id":"2508.14045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14045v1","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZNRXALNNK36A","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZNRXALNNK36A6GTT","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZNRXALNN","created_at":"2026-07-05T11:56:23Z"}],"graph_snapshots":[{"event_id":"sha256:c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a","target":"graph","created_at":"2026-07-05T11:56:23Z","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/2508.14045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Storytelling is a challenging multimodal task between Vision & Language, where the purpose is to generate a story for a stream of images. Its difficulty lies on the fact that the story should be both grounded to the image sequence but also narrative and coherent. The aim of this work is to balance between these aspects, by treating Visual Storytelling as a superset of Image Captioning, an approach quite different compared to most of prior relevant studies. This means that we firstly employ a vision-to-language model for obtaining captions of the input images, and then, these captions ar","authors_text":"Admitos Passadakis, Albert Gatt, Yingjin Song","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title":"From Image Captioning to Visual Storytelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14045","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:ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462","target":"record","created_at":"2026-07-05T11:56:23Z","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":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a"},"schema_version":"1.0","source":{"id":"2508.14045","kind":"arxiv","version":1}},"canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","first_computed_at":"2026-07-05T11:56:23.869145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:23.869145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y0sPSwVN7lEHiWU4I04H1z0rAFvRHfccA89PqXfOSFhOdm/wiUXcMLFsrFzhPMqIdeK9EPsTpcwz5eNgjPd6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:23.869584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462","sha256:c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a"],"state_sha256":"df5fd4a6cf63988c3ed6fb56a46de15c85ea86f9d58fa0433b891e32da8c7ed8"}