{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCUMYSDHKURTNVDKYMTEAPCSZR","short_pith_number":"pith:XCUMYSDH","schema_version":"1.0","canonical_sha256":"b8a8cc4867552336d46ac326403c52cc473abc556bbd84c744471a69143d5df8","source":{"kind":"arxiv","id":"2506.04034","version":1},"attestation_state":"computed","paper":{"title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junzhi Yu, Lei Zhang, Qing Jiang, Xingyu Chen, Zhaoyang Zeng","submitted_at":"2025-06-04T14:56:57Z","abstract_excerpt":"Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding bo"},"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":"2506.04034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T14:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"ef73c12d7dc60db1d261e1536d167f450d23b9ab8dabcdf1ec9bc307e0c4c90b","abstract_canon_sha256":"7ac24f5acbd2a76a099f460fc94342d2169b6b603b0a0a98990c2c90171c1817"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:55.967284Z","signature_b64":"RpdJLpZm+uMQJRrRQiFLsqswIHK++EF7v78837bdr6kpNymGij9r+zsqK0FW/8KfkpcNCZ0/jiLsFQ+iLxMaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a8cc4867552336d46ac326403c52cc473abc556bbd84c744471a69143d5df8","last_reissued_at":"2026-07-05T11:15:55.966683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:55.966683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junzhi Yu, Lei Zhang, Qing Jiang, Xingyu Chen, Zhaoyang Zeng","submitted_at":"2025-06-04T14:56:57Z","abstract_excerpt":"Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04034","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/2506.04034/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":"2506.04034","created_at":"2026-07-05T11:15:55.966769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04034v1","created_at":"2026-07-05T11:15:55.966769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04034","created_at":"2026-07-05T11:15:55.966769+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCUMYSDHKURT","created_at":"2026-07-05T11:15:55.966769+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCUMYSDHKURTNVDK","created_at":"2026-07-05T11:15:55.966769+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCUMYSDH","created_at":"2026-07-05T11:15:55.966769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08541","citing_title":"VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31174","citing_title":"Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03307","citing_title":"V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR","json":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR.json","graph_json":"https://pith.science/api/pith-number/XCUMYSDHKURTNVDKYMTEAPCSZR/graph.json","events_json":"https://pith.science/api/pith-number/XCUMYSDHKURTNVDKYMTEAPCSZR/events.json","paper":"https://pith.science/paper/XCUMYSDH"},"agent_actions":{"view_html":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR","download_json":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR.json","view_paper":"https://pith.science/paper/XCUMYSDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04034&json=true","fetch_graph":"https://pith.science/api/pith-number/XCUMYSDHKURTNVDKYMTEAPCSZR/graph.json","fetch_events":"https://pith.science/api/pith-number/XCUMYSDHKURTNVDKYMTEAPCSZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR/action/storage_attestation","attest_author":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR/action/author_attestation","sign_citation":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR/action/citation_signature","submit_replication":"https://pith.science/pith/XCUMYSDHKURTNVDKYMTEAPCSZR/action/replication_record"}},"created_at":"2026-07-05T11:15:55.966769+00:00","updated_at":"2026-07-05T11:15:55.966769+00:00"}