{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HGO6IF7RM3RSRSDOVHT7WA5NCQ","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":"8871315aee376cfa1dc7018805cd160ac6c0b056d85780f0c522da9b0ecb9445","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:56:09Z","title_canon_sha256":"bd9480a19cbb5a7d6190af5be0512bc0e3692243457009a9fbe3d4d851c43c88"},"schema_version":"1.0","source":{"id":"2503.12329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12329","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12329v1","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12329","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_12","alias_value":"HGO6IF7RM3RS","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_16","alias_value":"HGO6IF7RM3RSRSDO","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_8","alias_value":"HGO6IF7R","created_at":"2026-07-05T10:32:10Z"}],"graph_snapshots":[{"event_id":"sha256:2067298f39cfac5cdf577e2b25c5bfd4f67b9acdccb939a20bacf67e208bdec1","target":"graph","created_at":"2026-07-05T10:32:10Z","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/2503.12329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning has been a longstanding challenge in vision-language research. With the rise of LLMs, modern Vision-Language Models (VLMs) generate detailed and comprehensive image descriptions. However, benchmarking the quality of such captions remains unresolved. This paper addresses two key questions: (1) How well do current VLMs actually perform on image captioning, particularly compared to humans? We built CapArena, a platform with over 6000 pairwise caption battles and high-quality human preference votes. Our arena-style evaluation marks a milestone, showing that leading models like GPT","authors_text":"Chenyang Yan, Fangzhi Xu, Jiajun Chen, Jianbing Zhang, Jiaxin Fan, Kanzhi Cheng, Nuo Chen, Qiushi Sun, Wenpo Song, Zheng Ma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:56:09Z","title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12329","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":"sha256:68a6712c34627061fd70ae544a4ae9db8620f43810022c7eb9b058ed0100732a","target":"record","created_at":"2026-07-05T10:32:10Z","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":"8871315aee376cfa1dc7018805cd160ac6c0b056d85780f0c522da9b0ecb9445","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:56:09Z","title_canon_sha256":"bd9480a19cbb5a7d6190af5be0512bc0e3692243457009a9fbe3d4d851c43c88"},"schema_version":"1.0","source":{"id":"2503.12329","kind":"arxiv","version":1}},"canonical_sha256":"399de417f166e328c86ea9e7fb03ad141f2575f720964fbf4bb990395ab5e252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"399de417f166e328c86ea9e7fb03ad141f2575f720964fbf4bb990395ab5e252","first_computed_at":"2026-07-05T10:32:10.612711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:10.612711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3tWpoDaCg1zF656PvT0rtrT2OW4mcf/J7qFleVmEHTqguRxy74PrdA1TdklS3QjD572DtrHVjTk79HrCVlJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:10.613702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68a6712c34627061fd70ae544a4ae9db8620f43810022c7eb9b058ed0100732a","sha256:2067298f39cfac5cdf577e2b25c5bfd4f67b9acdccb939a20bacf67e208bdec1"],"state_sha256":"43d41c879e21587cfdec1684ce24e193860ddf2fd6349cb80ff585279eccffe0"}