{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VZF3AU33Y5A3HCNILAURNQLEFN","short_pith_number":"pith:VZF3AU33","schema_version":"1.0","canonical_sha256":"ae4bb0537bc741b389a8582916c1642b5b3a3da5ad51467433c988b388b58e90","source":{"kind":"arxiv","id":"2605.25706","version":1},"attestation_state":"computed","paper":{"title":"Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Zongjian Wu","submitted_at":"2026-05-25T11:05:37Z","abstract_excerpt":"Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC benchmarks often hold simple scenarios and the assumption that each expression maps to a unique object. These limitations hinder the deployment of REC models in open-world environments. To fill this gap, we introduce OpenRef, a new benchmark for REC in complex visual and linguistic scenarios. OpenRef features three key advancements: 1) Diverse visual scenarios: spa"},"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":"2605.25706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T11:05:37Z","cross_cats_sorted":[],"title_canon_sha256":"d8d32cb02533c2c357c7217acdbc9c3e46e06880b37c98d8e352d468b56e919b","abstract_canon_sha256":"92daf3a42b231d4d08eeba3a79d71b0d1302f9359fdf476c0fdced4842fa56bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:51.458821Z","signature_b64":"1WYdQjSaog67smsfawdofdr0HYW7OHaUdESpu3iWJMldHzLJCtFdtsL5RUDgT5sFLQIpHTRuBnGy5Cviz9WuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4bb0537bc741b389a8582916c1642b5b3a3da5ad51467433c988b388b58e90","last_reissued_at":"2026-05-26T02:04:51.458064Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:51.458064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Zongjian Wu","submitted_at":"2026-05-25T11:05:37Z","abstract_excerpt":"Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC benchmarks often hold simple scenarios and the assumption that each expression maps to a unique object. These limitations hinder the deployment of REC models in open-world environments. To fill this gap, we introduce OpenRef, a new benchmark for REC in complex visual and linguistic scenarios. OpenRef features three key advancements: 1) Diverse visual scenarios: spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25706","kind":"arxiv","version":1},"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/2605.25706/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":"2605.25706","created_at":"2026-05-26T02:04:51.458196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25706v1","created_at":"2026-05-26T02:04:51.458196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25706","created_at":"2026-05-26T02:04:51.458196+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZF3AU33Y5A3","created_at":"2026-05-26T02:04:51.458196+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZF3AU33Y5A3HCNI","created_at":"2026-05-26T02:04:51.458196+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZF3AU33","created_at":"2026-05-26T02:04:51.458196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN","json":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN.json","graph_json":"https://pith.science/api/pith-number/VZF3AU33Y5A3HCNILAURNQLEFN/graph.json","events_json":"https://pith.science/api/pith-number/VZF3AU33Y5A3HCNILAURNQLEFN/events.json","paper":"https://pith.science/paper/VZF3AU33"},"agent_actions":{"view_html":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN","download_json":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN.json","view_paper":"https://pith.science/paper/VZF3AU33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25706&json=true","fetch_graph":"https://pith.science/api/pith-number/VZF3AU33Y5A3HCNILAURNQLEFN/graph.json","fetch_events":"https://pith.science/api/pith-number/VZF3AU33Y5A3HCNILAURNQLEFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN/action/storage_attestation","attest_author":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN/action/author_attestation","sign_citation":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN/action/citation_signature","submit_replication":"https://pith.science/pith/VZF3AU33Y5A3HCNILAURNQLEFN/action/replication_record"}},"created_at":"2026-05-26T02:04:51.458196+00:00","updated_at":"2026-05-26T02:04:51.458196+00:00"}