{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DKIE47V6XABSE54YXGKVFFFMBX","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":"c6f560f6610d112fb76673c4b03a81dcf56bfde327e5a3a9c991cbfeda0286fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T17:42:05Z","title_canon_sha256":"9b93bf0faabb921020f4699bcf6e9fbe9f0cdb5d08e30bcf367af790f74a7fb5"},"schema_version":"1.0","source":{"id":"2408.13898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13898","created_at":"2026-07-05T08:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13898v1","created_at":"2026-07-05T08:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13898","created_at":"2026-07-05T08:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"DKIE47V6XABS","created_at":"2026-07-05T08:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"DKIE47V6XABSE54Y","created_at":"2026-07-05T08:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"DKIE47V6","created_at":"2026-07-05T08:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:4fdfb62e614628a847fbb7a441fcdc4d4c65bf990c2961b6df65fc544d588401","target":"graph","created_at":"2026-07-05T08:59:13Z","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/2408.13898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, large vision-language models have gained promising progress on many downstream tasks. However, they still suffer many challenges in fine-grained visual understanding tasks, such as object attribute comprehension. Besides, there have been growing efforts on the evaluations of large vision-language models, but lack of in-depth study of attribute comprehension and the visual language fine-tuning process. In this paper, we propose to evaluate the attribute comprehension ability of large vision-language models from two perspectives: attribute recognition and attribute hierarchy understan","authors_text":"Haiwen Zhang, Kongming Liang, Xinran Wang, Yuanzhi Liu, Zhanyu Ma, Zheqi He, Zixi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T17:42:05Z","title":"Evaluating Attribute Comprehension in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13898","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":"sha256:4d6aacfc6a41ac795891f5821a409f99e06983f961fe7acd5ca3617e8d79ca38","target":"record","created_at":"2026-07-05T08:59:13Z","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":"c6f560f6610d112fb76673c4b03a81dcf56bfde327e5a3a9c991cbfeda0286fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T17:42:05Z","title_canon_sha256":"9b93bf0faabb921020f4699bcf6e9fbe9f0cdb5d08e30bcf367af790f74a7fb5"},"schema_version":"1.0","source":{"id":"2408.13898","kind":"arxiv","version":1}},"canonical_sha256":"1a904e7ebeb803227798b9955294ac0ddf5bea8121521bad51617aa7e54df5ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a904e7ebeb803227798b9955294ac0ddf5bea8121521bad51617aa7e54df5ff","first_computed_at":"2026-07-05T08:59:13.568834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:13.568834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6D+nsFCYdZ9FLNwOIxvbdhdR2BF7JRP3Nxx8e7bOp/WkJ9IQHvYasMCej1W+YjX+36pvMlemM/z+UsNm8yAWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:13.569227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d6aacfc6a41ac795891f5821a409f99e06983f961fe7acd5ca3617e8d79ca38","sha256:4fdfb62e614628a847fbb7a441fcdc4d4c65bf990c2961b6df65fc544d588401"],"state_sha256":"03b08b22360b96865e2950a023badbe5d33b7e98d81c809763f41d4c5cce6c39"}