{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HGO6IF7RM3RSRSDOVHT7WA5NCQ","short_pith_number":"pith:HGO6IF7R","canonical_record":{"source":{"id":"2503.12329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:56:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bd9480a19cbb5a7d6190af5be0512bc0e3692243457009a9fbe3d4d851c43c88","abstract_canon_sha256":"8871315aee376cfa1dc7018805cd160ac6c0b056d85780f0c522da9b0ecb9445"},"schema_version":"1.0"},"canonical_sha256":"399de417f166e328c86ea9e7fb03ad141f2575f720964fbf4bb990395ab5e252","source":{"kind":"arxiv","id":"2503.12329","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HGO6IF7RM3RSRSDOVHT7WA5NCQ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:56:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bd9480a19cbb5a7d6190af5be0512bc0e3692243457009a9fbe3d4d851c43c88","abstract_canon_sha256":"8871315aee376cfa1dc7018805cd160ac6c0b056d85780f0c522da9b0ecb9445"},"schema_version":"1.0"},"canonical_sha256":"399de417f166e328c86ea9e7fb03ad141f2575f720964fbf4bb990395ab5e252","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:10.613702Z","signature_b64":"S3tWpoDaCg1zF656PvT0rtrT2OW4mcf/J7qFleVmEHTqguRxy74PrdA1TdklS3QjD572DtrHVjTk79HrCVlJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"399de417f166e328c86ea9e7fb03ad141f2575f720964fbf4bb990395ab5e252","last_reissued_at":"2026-07-05T10:32:10.612711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:10.612711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12329","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBIuIE7OcJj6Zss6wwD9FStQUyvia7OXSgzN1S7aItn1u9hYV5gNJPi9HQ3G8xEzuHozbk8Mte4eyv8wY/6mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:25:31.395222Z"},"content_sha256":"68a6712c34627061fd70ae544a4ae9db8620f43810022c7eb9b058ed0100732a","schema_version":"1.0","event_id":"sha256:68a6712c34627061fd70ae544a4ae9db8620f43810022c7eb9b058ed0100732a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HGO6IF7RM3RSRSDOVHT7WA5NCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenyang Yan, Fangzhi Xu, Jiajun Chen, Jianbing Zhang, Jiaxin Fan, Kanzhi Cheng, Nuo Chen, Qiushi Sun, Wenpo Song, Zheng Ma","submitted_at":"2025-03-16T02:56:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12329","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.12329/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRFsxKSr7oc6v1hicVCYL9LcrvOd8CQklvghya36PAYtEIMoH9YV8Rxw+YpcqtA6TKSDSWiLOe7O0cjNgftMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:25:31.395749Z"},"content_sha256":"2067298f39cfac5cdf577e2b25c5bfd4f67b9acdccb939a20bacf67e208bdec1","schema_version":"1.0","event_id":"sha256:2067298f39cfac5cdf577e2b25c5bfd4f67b9acdccb939a20bacf67e208bdec1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/bundle.json","state_url":"https://pith.science/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T16:25:31Z","links":{"resolver":"https://pith.science/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ","bundle":"https://pith.science/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/bundle.json","state":"https://pith.science/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGO6IF7RM3RSRSDOVHT7WA5NCQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3UovdE/lLpBEhXnJnAg/QRR4t0OfbJ1Qpg+DlPeW0lmv4iFSvvH6p1Y8K3m6yNj9jKCt/Gm7uRjLONlHhwhMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:25:31.401207Z","bundle_sha256":"c6a09a1ac4f7a1c18ca14bf09ad90131927a9b9d1b0e488846b6dc9aec93cdbc"}}