{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5KXKM3WFWOCIAUAJYVWEHOMCWM","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":"0c214b71fb473b5f07943ccf9bd13791c45d877f5bf44048fb6a8328c891559b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T04:54:32Z","title_canon_sha256":"f79c03b746f88df7b935175d908d36db9cdf330875210219e506b646dae66d84"},"schema_version":"1.0","source":{"id":"2308.13177","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13177","created_at":"2026-07-05T07:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13177v2","created_at":"2026-07-05T07:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13177","created_at":"2026-07-05T07:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"5KXKM3WFWOCI","created_at":"2026-07-05T07:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"5KXKM3WFWOCIAUAJ","created_at":"2026-07-05T07:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"5KXKM3WF","created_at":"2026-07-05T07:24:53Z"}],"graph_snapshots":[{"event_id":"sha256:1af5ae69b016ed2c216e9e48eb3199ad06d75853d753f19f414ff468c13b46fd","target":"graph","created_at":"2026-07-05T07:24:53Z","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/2308.13177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object detection (OD) in computer vision has made significant progress in recent years, transitioning from closed-set labels to open-vocabulary detection (OVD) based on large-scale vision-language pre-training (VLP). However, current evaluation methods and datasets are limited to testing generalization over object types and referral expressions, which do not provide a systematic, fine-grained, and accurate benchmark of OVD models' abilities. In this paper, we propose a new benchmark named OVDEval, which includes 9 sub-tasks and introduces evaluations on commonsense knowledge, attribute underst","authors_text":"Chunxin Fang, Jiajia Liao, Kyusong Lee, Peng Liu, Qianqian Zhang, Qing Wang, Tiancheng Zhao, Yiyang Yao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T04:54:32Z","title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13177","kind":"arxiv","version":2},"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:dda68018b3d60edeb4425d1009a796768e56404c5c47ee61e995d83264bae7c5","target":"record","created_at":"2026-07-05T07:24:53Z","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":"0c214b71fb473b5f07943ccf9bd13791c45d877f5bf44048fb6a8328c891559b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T04:54:32Z","title_canon_sha256":"f79c03b746f88df7b935175d908d36db9cdf330875210219e506b646dae66d84"},"schema_version":"1.0","source":{"id":"2308.13177","kind":"arxiv","version":2}},"canonical_sha256":"eaaea66ec5b384805009c56c43b982b32f37c5d18959adaf8e30a9342436095d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaaea66ec5b384805009c56c43b982b32f37c5d18959adaf8e30a9342436095d","first_computed_at":"2026-07-05T07:24:53.154881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:53.154881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6frJP8Ur9FchYGHtPsP1MeeXaJ1O+yxtgk2VuB+Srse+atlg2O9gAiJ6FLPkR0fH6wBK9PqI8SplraXdOk5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:53.155388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13177","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dda68018b3d60edeb4425d1009a796768e56404c5c47ee61e995d83264bae7c5","sha256:1af5ae69b016ed2c216e9e48eb3199ad06d75853d753f19f414ff468c13b46fd"],"state_sha256":"81288e74dce3523fb29a5f367fdc10093ffdc6ab02e259184e02a21684c326e8"}