{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3QX2HLFUQYLUBJSATJ22GOPQSH","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":"0c08a48403bab3559fb83fc22416bb329c2910c672ba92cc8b2f62fcf4ffe357","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T20:27:16Z","title_canon_sha256":"f72892dce2cc67e2420de3ab5cd75ed41997b6cecd40b1cdbdd1ed869917b4e2"},"schema_version":"1.0","source":{"id":"2310.17770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17770","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17770v1","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17770","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"3QX2HLFUQYLU","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"3QX2HLFUQYLUBJSA","created_at":"2026-07-05T07:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"3QX2HLFU","created_at":"2026-07-05T07:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:d11309c62d14687fb1563d3caa3d51646466fe664e6db62dd51a0eab4683c60c","target":"graph","created_at":"2026-07-05T07:05:52Z","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/2310.17770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A proper evaluation of stories generated for a sequence of images -- the task commonly referred to as visual storytelling -- must consider multiple aspects, such as coherence, grammatical correctness, and visual grounding. In this work, we focus on evaluating the degree of grounding, that is, the extent to which a story is about the entities shown in the images. We analyze current metrics, both designed for this purpose and for general vision-text alignment. Given their observed shortcomings, we propose a novel evaluation tool, GROOViST, that accounts for cross-modal dependencies, temporal mis","authors_text":"Aditya K Surikuchi, Raquel Fern\\'andez, Sandro Pezzelle","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T20:27:16Z","title":"GROOViST: A Metric for Grounding Objects in Visual Storytelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17770","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":"sha256:1f358776a4e93e0856d235272c5c5b7e2fd5edfe2bd226144f6db131a91fcc29","target":"record","created_at":"2026-07-05T07:05:52Z","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":"0c08a48403bab3559fb83fc22416bb329c2910c672ba92cc8b2f62fcf4ffe357","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T20:27:16Z","title_canon_sha256":"f72892dce2cc67e2420de3ab5cd75ed41997b6cecd40b1cdbdd1ed869917b4e2"},"schema_version":"1.0","source":{"id":"2310.17770","kind":"arxiv","version":1}},"canonical_sha256":"dc2fa3acb4861740a6409a75a339f091e0b1ea8adb6d852b00c2991e280c67d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc2fa3acb4861740a6409a75a339f091e0b1ea8adb6d852b00c2991e280c67d1","first_computed_at":"2026-07-05T07:05:52.337521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:52.337521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dH04oPKNZpZKnm4pHFb1GIIiQBS/hL+Ak6bTUJGKGraWwmvkuBC9aYwVFNK6C+e7znvqJWs93zezW+taMg01Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:52.338012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f358776a4e93e0856d235272c5c5b7e2fd5edfe2bd226144f6db131a91fcc29","sha256:d11309c62d14687fb1563d3caa3d51646466fe664e6db62dd51a0eab4683c60c"],"state_sha256":"6c3172d8614882368d2d8233e5ee252c1d47984024c9e5c36b7549a85d765864"}