{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TFP4B26X6F7LQLPBNGHG5USDUN","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":"b0f7025229c66b0e67366e256b0ddde133f3686546cdbe9ab134f1bc0c5372f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T17:59:56Z","title_canon_sha256":"ae8ee1c747c85eae97186e13ec009d8fe8913ecf2e6e58d5fc9d096a88d15dcd"},"schema_version":"1.0","source":{"id":"2207.03482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.03482","created_at":"2026-07-05T05:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"2207.03482v3","created_at":"2026-07-05T05:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03482","created_at":"2026-07-05T05:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"TFP4B26X6F7L","created_at":"2026-07-05T05:20:12Z"},{"alias_kind":"pith_short_16","alias_value":"TFP4B26X6F7LQLPB","created_at":"2026-07-05T05:20:12Z"},{"alias_kind":"pith_short_8","alias_value":"TFP4B26X","created_at":"2026-07-05T05:20:12Z"}],"graph_snapshots":[{"event_id":"sha256:b69a542432816bc375ef137b906e0ef4ae837f43975eb60ba266ed4763f5a4f1","target":"graph","created_at":"2026-07-05T05:20:12Z","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/2207.03482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T17:59:56Z","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03482","kind":"arxiv","version":3},"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":"sha256:9894a71664aa5b6a0238496d6f4e9e64e2e6baee444f407fdc6f3281d6290df4","target":"record","created_at":"2026-07-05T05:20:12Z","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":"b0f7025229c66b0e67366e256b0ddde133f3686546cdbe9ab134f1bc0c5372f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T17:59:56Z","title_canon_sha256":"ae8ee1c747c85eae97186e13ec009d8fe8913ecf2e6e58d5fc9d096a88d15dcd"},"schema_version":"1.0","source":{"id":"2207.03482","kind":"arxiv","version":3}},"canonical_sha256":"995fc0ebd7f17eb82de1698e6ed243a3595cbe369c40c49f5f82ef7dea3491eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"995fc0ebd7f17eb82de1698e6ed243a3595cbe369c40c49f5f82ef7dea3491eb","first_computed_at":"2026-07-05T05:20:12.694867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:20:12.694867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OzIvnA3b5hBYwgQwzasx2jV/1YLl7HC5p5lGBBjdbOn07fEwtn8GxdZ36lZt9JCXTms3js56h/tCvM3SrKMABA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:20:12.695422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.03482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9894a71664aa5b6a0238496d6f4e9e64e2e6baee444f407fdc6f3281d6290df4","sha256:b69a542432816bc375ef137b906e0ef4ae837f43975eb60ba266ed4763f5a4f1"],"state_sha256":"0f33b38a01aa0bd486f36cd6b3e3eb6cd97f15f14a00f5e95560bb436e0955b2"}