{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IP2TETBAMYSAK6DO6ZWSNOJI7W","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":"ec76f0e419193c1d3deb1fbcf0b84b8c6a2721e80e7cc601edfa1eb66c67f7fc","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T14:48:15Z","title_canon_sha256":"36001c8b568472f2cfeb057525f16cb813201a2d5a7398ae78395c5fbe6092a6"},"schema_version":"1.0","source":{"id":"2407.04559","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04559","created_at":"2026-07-05T09:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04559v4","created_at":"2026-07-05T09:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04559","created_at":"2026-07-05T09:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"IP2TETBAMYSA","created_at":"2026-07-05T09:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"IP2TETBAMYSAK6DO","created_at":"2026-07-05T09:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"IP2TETBA","created_at":"2026-07-05T09:25:45Z"}],"graph_snapshots":[{"event_id":"sha256:2aca5c5096e3d447f0e7ecaeec7fdcb993355c8e88e1199e8a3632b0ecd32aee","target":"graph","created_at":"2026-07-05T09:25:45Z","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/2407.04559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story 'good'. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLa","authors_text":"Aditya K Surikuchi, Raquel Fern\\'andez, Sandro Pezzelle","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T14:48:15Z","title":"Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04559","kind":"arxiv","version":4},"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":"sha256:90f7e73db882245824b44a23e6dd46b621cc6ff9240a1918cdd639cdc02d90ac","target":"record","created_at":"2026-07-05T09:25:45Z","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":"ec76f0e419193c1d3deb1fbcf0b84b8c6a2721e80e7cc601edfa1eb66c67f7fc","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T14:48:15Z","title_canon_sha256":"36001c8b568472f2cfeb057525f16cb813201a2d5a7398ae78395c5fbe6092a6"},"schema_version":"1.0","source":{"id":"2407.04559","kind":"arxiv","version":4}},"canonical_sha256":"43f5324c20662405786ef66d26b928fdb5f2bc9d2aa0e4ca7f887deb7bc4a1e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43f5324c20662405786ef66d26b928fdb5f2bc9d2aa0e4ca7f887deb7bc4a1e3","first_computed_at":"2026-07-05T09:25:45.086554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:45.086554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mUJtBkcyWQbWH0bapE7o2vdKyKqznRr638jhTNXvuwzBVVzlBDfWgtUrntgQixpSkH8OIcPczjAwT52dJ3mBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:45.087039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04559","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90f7e73db882245824b44a23e6dd46b621cc6ff9240a1918cdd639cdc02d90ac","sha256:2aca5c5096e3d447f0e7ecaeec7fdcb993355c8e88e1199e8a3632b0ecd32aee"],"state_sha256":"a9e83e18a77ab98904b0fc8585b0e90ac99ac4f87b338ffe64e0c6adfe64498b"}