{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TFP4B26X6F7LQLPBNGHG5USDUN","short_pith_number":"pith:TFP4B26X","schema_version":"1.0","canonical_sha256":"995fc0ebd7f17eb82de1698e6ed243a3595cbe369c40c49f5f82ef7dea3491eb","source":{"kind":"arxiv","id":"2207.03482","version":3},"attestation_state":"computed","paper":{"title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-07-07T17:59:56Z","abstract_excerpt":"Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local "},"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":"2207.03482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T17:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae8ee1c747c85eae97186e13ec009d8fe8913ecf2e6e58d5fc9d096a88d15dcd","abstract_canon_sha256":"b0f7025229c66b0e67366e256b0ddde133f3686546cdbe9ab134f1bc0c5372f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:12.695422Z","signature_b64":"OzIvnA3b5hBYwgQwzasx2jV/1YLl7HC5p5lGBBjdbOn07fEwtn8GxdZ36lZt9JCXTms3js56h/tCvM3SrKMABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"995fc0ebd7f17eb82de1698e6ed243a3595cbe369c40c49f5f82ef7dea3491eb","last_reissued_at":"2026-07-05T05:20:12.694867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:12.694867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-07-07T17:59:56Z","abstract_excerpt":"Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03482","kind":"arxiv","version":3},"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/2207.03482/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":"2207.03482","created_at":"2026-07-05T05:20:12.694929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03482v3","created_at":"2026-07-05T05:20:12.694929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03482","created_at":"2026-07-05T05:20:12.694929+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFP4B26X6F7L","created_at":"2026-07-05T05:20:12.694929+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFP4B26X6F7LQLPB","created_at":"2026-07-05T05:20:12.694929+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFP4B26X","created_at":"2026-07-05T05:20:12.694929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN","json":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN.json","graph_json":"https://pith.science/api/pith-number/TFP4B26X6F7LQLPBNGHG5USDUN/graph.json","events_json":"https://pith.science/api/pith-number/TFP4B26X6F7LQLPBNGHG5USDUN/events.json","paper":"https://pith.science/paper/TFP4B26X"},"agent_actions":{"view_html":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN","download_json":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN.json","view_paper":"https://pith.science/paper/TFP4B26X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03482&json=true","fetch_graph":"https://pith.science/api/pith-number/TFP4B26X6F7LQLPBNGHG5USDUN/graph.json","fetch_events":"https://pith.science/api/pith-number/TFP4B26X6F7LQLPBNGHG5USDUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN/action/storage_attestation","attest_author":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN/action/author_attestation","sign_citation":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN/action/citation_signature","submit_replication":"https://pith.science/pith/TFP4B26X6F7LQLPBNGHG5USDUN/action/replication_record"}},"created_at":"2026-07-05T05:20:12.694929+00:00","updated_at":"2026-07-05T05:20:12.694929+00:00"}