{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C5KGWJNDFABC2WP5WENZPHA3BO","short_pith_number":"pith:C5KGWJND","schema_version":"1.0","canonical_sha256":"17546b25a328022d59fdb11b979c1b0bba61c3babdfb2f4d6f52385bf60c2f31","source":{"kind":"arxiv","id":"2204.05991","version":2},"attestation_state":"computed","paper":{"title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Matt Gardner, Sameer Singh, Sanjay Subramanian, Trevor Darrell, William Merrill","submitted_at":"2022-04-12T17:55:38Z","abstract_excerpt":"Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP's contrastive pre-training objective"},"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":"2204.05991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-12T17:55:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"71028221d7db8685e4eb2562f015bd8a188d70d246ebd8176390a4c3ef7adbf9","abstract_canon_sha256":"631d1ee0d72a1a5c547639578ff6025405dbcf1912efe4d5e24d36c0c9cc10e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:58.025087Z","signature_b64":"kqVPlTVhEu9Ds4M2ZAcAzl7WuYshlSQ+q/tCMJR/TcjGgjjvc8sT0R7NdDJVPcuT32ESuOA/f3AlBJZCqs0NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17546b25a328022d59fdb11b979c1b0bba61c3babdfb2f4d6f52385bf60c2f31","last_reissued_at":"2026-07-05T04:19:58.024636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:58.024636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Matt Gardner, Sameer Singh, Sanjay Subramanian, Trevor Darrell, William Merrill","submitted_at":"2022-04-12T17:55:38Z","abstract_excerpt":"Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP's contrastive pre-training objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05991","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/2204.05991/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":"2204.05991","created_at":"2026-07-05T04:19:58.024686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05991v2","created_at":"2026-07-05T04:19:58.024686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05991","created_at":"2026-07-05T04:19:58.024686+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5KGWJNDFABC","created_at":"2026-07-05T04:19:58.024686+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5KGWJNDFABC2WP5","created_at":"2026-07-05T04:19:58.024686+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5KGWJND","created_at":"2026-07-05T04:19:58.024686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07965","citing_title":"Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07953","citing_title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08110","citing_title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO","json":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO.json","graph_json":"https://pith.science/api/pith-number/C5KGWJNDFABC2WP5WENZPHA3BO/graph.json","events_json":"https://pith.science/api/pith-number/C5KGWJNDFABC2WP5WENZPHA3BO/events.json","paper":"https://pith.science/paper/C5KGWJND"},"agent_actions":{"view_html":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO","download_json":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO.json","view_paper":"https://pith.science/paper/C5KGWJND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05991&json=true","fetch_graph":"https://pith.science/api/pith-number/C5KGWJNDFABC2WP5WENZPHA3BO/graph.json","fetch_events":"https://pith.science/api/pith-number/C5KGWJNDFABC2WP5WENZPHA3BO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO/action/storage_attestation","attest_author":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO/action/author_attestation","sign_citation":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO/action/citation_signature","submit_replication":"https://pith.science/pith/C5KGWJNDFABC2WP5WENZPHA3BO/action/replication_record"}},"created_at":"2026-07-05T04:19:58.024686+00:00","updated_at":"2026-07-05T04:19:58.024686+00:00"}