{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DKIE47V6XABSE54YXGKVFFFMBX","short_pith_number":"pith:DKIE47V6","schema_version":"1.0","canonical_sha256":"1a904e7ebeb803227798b9955294ac0ddf5bea8121521bad51617aa7e54df5ff","source":{"kind":"arxiv","id":"2408.13898","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Attribute Comprehension in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Zhang, Kongming Liang, Xinran Wang, Yuanzhi Liu, Zhanyu Ma, Zheqi He, Zixi Yang","submitted_at":"2024-08-25T17:42:05Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.13898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T17:42:05Z","cross_cats_sorted":[],"title_canon_sha256":"9b93bf0faabb921020f4699bcf6e9fbe9f0cdb5d08e30bcf367af790f74a7fb5","abstract_canon_sha256":"c6f560f6610d112fb76673c4b03a81dcf56bfde327e5a3a9c991cbfeda0286fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:13.569227Z","signature_b64":"6D+nsFCYdZ9FLNwOIxvbdhdR2BF7JRP3Nxx8e7bOp/WkJ9IQHvYasMCej1W+YjX+36pvMlemM/z+UsNm8yAWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a904e7ebeb803227798b9955294ac0ddf5bea8121521bad51617aa7e54df5ff","last_reissued_at":"2026-07-05T08:59:13.568834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:13.568834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Attribute Comprehension in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Zhang, Kongming Liang, Xinran Wang, Yuanzhi Liu, Zhanyu Ma, Zheqi He, Zixi Yang","submitted_at":"2024-08-25T17:42:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13898","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/2408.13898/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.13898","created_at":"2026-07-05T08:59:13.568890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13898v1","created_at":"2026-07-05T08:59:13.568890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13898","created_at":"2026-07-05T08:59:13.568890+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKIE47V6XABS","created_at":"2026-07-05T08:59:13.568890+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKIE47V6XABSE54Y","created_at":"2026-07-05T08:59:13.568890+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKIE47V6","created_at":"2026-07-05T08:59:13.568890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX","json":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX.json","graph_json":"https://pith.science/api/pith-number/DKIE47V6XABSE54YXGKVFFFMBX/graph.json","events_json":"https://pith.science/api/pith-number/DKIE47V6XABSE54YXGKVFFFMBX/events.json","paper":"https://pith.science/paper/DKIE47V6"},"agent_actions":{"view_html":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX","download_json":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX.json","view_paper":"https://pith.science/paper/DKIE47V6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13898&json=true","fetch_graph":"https://pith.science/api/pith-number/DKIE47V6XABSE54YXGKVFFFMBX/graph.json","fetch_events":"https://pith.science/api/pith-number/DKIE47V6XABSE54YXGKVFFFMBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX/action/storage_attestation","attest_author":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX/action/author_attestation","sign_citation":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX/action/citation_signature","submit_replication":"https://pith.science/pith/DKIE47V6XABSE54YXGKVFFFMBX/action/replication_record"}},"created_at":"2026-07-05T08:59:13.568890+00:00","updated_at":"2026-07-05T08:59:13.568890+00:00"}