{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HSXMZTVIETHPLUPTHWF2BDQGDF","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":"ff359d8994e6c3610194ff94b8ecde08f3339bf33e0873e3c704f160647f76fa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:23:12Z","title_canon_sha256":"93792171128400e757770d6e5d94be321ba8cfbabc0f10db23645efde285e473"},"schema_version":"1.0","source":{"id":"2412.13647","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13647","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13647v2","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13647","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"HSXMZTVIETHP","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"HSXMZTVIETHPLUPT","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"HSXMZTVI","created_at":"2026-07-05T09:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:185f3c913988cb6d29578e63120a31060d6462edc612d291051b2033775535f1","target":"graph","created_at":"2026-07-05T09:51:40Z","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/2412.13647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation metric of visual captioning is important yet not thoroughly explored. Traditional metrics like BLEU, METEOR, CIDEr, and ROUGE often miss semantic depth, while trained metrics such as CLIP-Score, PAC-S, and Polos are limited in zero-shot scenarios. Advanced Language Model-based metrics also struggle with aligning to nuanced human preferences. To address these issues, we introduce G-VEval, a novel metric inspired by G-Eval and powered by the new GPT-4o. G-VEval uses chain-of-thought reasoning in large multimodal models and supports three modes: reference-free, reference-only, and comb","authors_text":"Dit-Yan Yeung, Sirui He, Tony Cheng Tong, Zhiwen Shao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:23:12Z","title":"G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13647","kind":"arxiv","version":2},"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":"sha256:79be7d877cda67ae6ab366b5c91c4cb81f7f1f308b1d1c0bcee72a30d5530091","target":"record","created_at":"2026-07-05T09:51:40Z","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":"ff359d8994e6c3610194ff94b8ecde08f3339bf33e0873e3c704f160647f76fa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:23:12Z","title_canon_sha256":"93792171128400e757770d6e5d94be321ba8cfbabc0f10db23645efde285e473"},"schema_version":"1.0","source":{"id":"2412.13647","kind":"arxiv","version":2}},"canonical_sha256":"3caecccea824cef5d1f33d8ba08e061971d77d68a74509c874c5ab328380c60f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3caecccea824cef5d1f33d8ba08e061971d77d68a74509c874c5ab328380c60f","first_computed_at":"2026-07-05T09:51:40.790680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:40.790680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wagIwsxVtHFL21YElUiu0SqnnKG5I+xuk4lGygS6WEn5B69zOsQF7a1VFRIIf/kUWHd7V2VA7aBjBads1q5HBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:40.791171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13647","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79be7d877cda67ae6ab366b5c91c4cb81f7f1f308b1d1c0bcee72a30d5530091","sha256:185f3c913988cb6d29578e63120a31060d6462edc612d291051b2033775535f1"],"state_sha256":"56385bb3d28e5178532ea9f99069d0641ef3e7d4fdb49a77616771eb00df1aac"}