{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMZIMESY3CP6SW7AKKIFTR6IMG","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":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed"},"schema_version":"1.0","source":{"id":"2407.18589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18589v1","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_12","alias_value":"FMZIMESY3CP6","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_16","alias_value":"FMZIMESY3CP6SW7A","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_8","alias_value":"FMZIMESY","created_at":"2026-07-05T08:48:52Z"}],"graph_snapshots":[{"event_id":"sha256:58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03","target":"graph","created_at":"2026-07-05T08:48:52Z","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/2407.18589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to evaluate descriptive captions with abundant visual details produced by advanced multimodal large language models, due to their heavy reliance on limited human-annotated references. In contrast, previous reference-free metrics have been proven effective via CLIP cross-modality similarity. Nonetheless, CLIP-based metrics, constrained by their solution of global image-text compatibility, often have a deficiency in detecting","authors_text":"Bo Chen, Hao Zhang, Jianqiao Sun, Tiansheng Wen, Yan Xie, Yudi Su, Zequn Zeng, Zhengjue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18589","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:dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220","target":"record","created_at":"2026-07-05T08:48:52Z","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":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed"},"schema_version":"1.0","source":{"id":"2407.18589","kind":"arxiv","version":1}},"canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","first_computed_at":"2026-07-05T08:48:52.005477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:52.005477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rf5aFJr3W86qAl+WtgQER83tsLrYxvhqj0OQpgw4/6K3jQ0zsoNKwxX/Zlq0BylqvHVr8GW4F1xIckvoZCAKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:52.005910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220","sha256:58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03"],"state_sha256":"f7cd424824901197f08546dc1ee665acd25b873bf1aae0b5d4ceb4a25482b8fc"}