{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KXKM3WFWOCIAUAJYVWEHOMCWM","short_pith_number":"pith:5KXKM3WF","schema_version":"1.0","canonical_sha256":"eaaea66ec5b384805009c56c43b982b32f37c5d18959adaf8e30a9342436095d","source":{"kind":"arxiv","id":"2308.13177","version":2},"attestation_state":"computed","paper":{"title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunxin Fang, Jiajia Liao, Kyusong Lee, Peng Liu, Qianqian Zhang, Qing Wang, Tiancheng Zhao, Yiyang Yao","submitted_at":"2023-08-25T04:54:32Z","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"},"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":"2308.13177","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T04:54:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f79c03b746f88df7b935175d908d36db9cdf330875210219e506b646dae66d84","abstract_canon_sha256":"0c214b71fb473b5f07943ccf9bd13791c45d877f5bf44048fb6a8328c891559b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:53.155388Z","signature_b64":"d6frJP8Ur9FchYGHtPsP1MeeXaJ1O+yxtgk2VuB+Srse+atlg2O9gAiJ6FLPkR0fH6wBK9PqI8SplraXdOk5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaaea66ec5b384805009c56c43b982b32f37c5d18959adaf8e30a9342436095d","last_reissued_at":"2026-07-05T07:24:53.154881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:53.154881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunxin Fang, Jiajia Liao, Kyusong Lee, Peng Liu, Qianqian Zhang, Qing Wang, Tiancheng Zhao, Yiyang Yao","submitted_at":"2023-08-25T04:54:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13177","kind":"arxiv","version":2},"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/2308.13177/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":"2308.13177","created_at":"2026-07-05T07:24:53.154939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13177v2","created_at":"2026-07-05T07:24:53.154939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13177","created_at":"2026-07-05T07:24:53.154939+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KXKM3WFWOCI","created_at":"2026-07-05T07:24:53.154939+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KXKM3WFWOCIAUAJ","created_at":"2026-07-05T07:24:53.154939+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KXKM3WF","created_at":"2026-07-05T07:24:53.154939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.15879","citing_title":"GRIT: Teaching MLLMs to Think with Images","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07615","citing_title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM","json":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM.json","graph_json":"https://pith.science/api/pith-number/5KXKM3WFWOCIAUAJYVWEHOMCWM/graph.json","events_json":"https://pith.science/api/pith-number/5KXKM3WFWOCIAUAJYVWEHOMCWM/events.json","paper":"https://pith.science/paper/5KXKM3WF"},"agent_actions":{"view_html":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM","download_json":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM.json","view_paper":"https://pith.science/paper/5KXKM3WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13177&json=true","fetch_graph":"https://pith.science/api/pith-number/5KXKM3WFWOCIAUAJYVWEHOMCWM/graph.json","fetch_events":"https://pith.science/api/pith-number/5KXKM3WFWOCIAUAJYVWEHOMCWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM/action/storage_attestation","attest_author":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM/action/author_attestation","sign_citation":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM/action/citation_signature","submit_replication":"https://pith.science/pith/5KXKM3WFWOCIAUAJYVWEHOMCWM/action/replication_record"}},"created_at":"2026-07-05T07:24:53.154939+00:00","updated_at":"2026-07-05T07:24:53.154939+00:00"}