{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PVKPIFFDIQPYIBD5AJ32I7SB6U","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":"6c3c6d509dfef786361b9a73f2cbabcc91eda1c95711b4c382716aff6bdbd4b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T13:54:12Z","title_canon_sha256":"68c1c8f1fcd60d0f297c9ea8e7cbd9737f4bcb501c74e107463badb7fff749d1"},"schema_version":"1.0","source":{"id":"2405.19092","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19092","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19092v4","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19092","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"PVKPIFFDIQPY","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_16","alias_value":"PVKPIFFDIQPYIBD5","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_8","alias_value":"PVKPIFFD","created_at":"2026-07-05T08:41:03Z"}],"graph_snapshots":[{"event_id":"sha256:b9ae71c7cc801f216398155bc27d9e95f74a39a8f1fc8899ae4757ed457ce091","target":"graph","created_at":"2026-07-05T08:41:03Z","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/2405.19092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning has long been regarded as a fundamental task in visual understanding. Recently, however, few large vision-language model (LVLM) research discusses model's image captioning performance because of the outdated short-caption benchmarks and unreliable evaluation metrics. In this work, we propose to benchmark detail image caption task by curating high-quality evaluation datasets annotated by human experts, GPT-4V and Gemini-1.5-Pro. We also design a more reliable caption evaluation metric called CAPTURE (CAPtion evaluation by exTracting and coUpling coRE information). CAPTURE extra","authors_text":"Bohong Wu, Haoyuan Guo, Hongyuan Dong, Jiacong Wang, Jiawen Li, Yuan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T13:54:12Z","title":"Benchmarking and Improving Detail Image Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19092","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:b316f452bd5ea2240848f8ae9da5eb41ed034640652d02f035e3995c3a6c140c","target":"record","created_at":"2026-07-05T08:41:03Z","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":"6c3c6d509dfef786361b9a73f2cbabcc91eda1c95711b4c382716aff6bdbd4b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T13:54:12Z","title_canon_sha256":"68c1c8f1fcd60d0f297c9ea8e7cbd9737f4bcb501c74e107463badb7fff749d1"},"schema_version":"1.0","source":{"id":"2405.19092","kind":"arxiv","version":4}},"canonical_sha256":"7d54f414a3441f84047d0277a47e41f50d4b8e1ed76d715336437c49e0d22a86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d54f414a3441f84047d0277a47e41f50d4b8e1ed76d715336437c49e0d22a86","first_computed_at":"2026-07-05T08:41:03.352898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:03.352898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bXh4Zdf+SI1YrW7CA3EOBWokPT+YGNGhIzvk4BJE68qRx6rtEVsx3FtmoKOovF6nay+v5MsYDmBx1BKb9QGoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:03.353390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19092","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b316f452bd5ea2240848f8ae9da5eb41ed034640652d02f035e3995c3a6c140c","sha256:b9ae71c7cc801f216398155bc27d9e95f74a39a8f1fc8899ae4757ed457ce091"],"state_sha256":"757450bf61618f7a934386ed9d6afaa6fdd1ed4ce225f42f9a3ec93847141a39"}