{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MECDCQSSCE7YTHVTKPAGOIZHJU","short_pith_number":"pith:MECDCQSS","schema_version":"1.0","canonical_sha256":"6104314252113f899eb353c06723274d0e77bc799d2f1025d2eddbf76e679e66","source":{"kind":"arxiv","id":"2403.02330","version":1},"attestation_state":"computed","paper":{"title":"RegionGPT: Towards Region Understanding Vision Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxu Yin, Ka Chun Cheung, Ping Luo, Qiushan Guo, Shalini De Mello, Sifei Liu, Wonmin Byeon, Yizhou Yu","submitted_at":"2024-03-04T18:58:08Z","abstract_excerpt":"Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions. To address this, we introduce RegionGPT (short as RGPT), a novel framework designed for complex region-level captioning and understanding. RGPT enhances the spatial awareness of regional representation with simple yet effective modifications to e"},"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":"2403.02330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:58:08Z","cross_cats_sorted":[],"title_canon_sha256":"5460d0e06c1057e684f2b242c5ac95eae2d2a92b4020f3bb36972095bae1f691","abstract_canon_sha256":"08bbdfd58fb10d6b127c93c5266898e6f296d916b6c5d39ab58e8641e50684a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:59.514471Z","signature_b64":"Gk4JaPFi7qwLT/hV2mbs5jv1jw3fzRh2nN4uPjOl+Eob61G+1lQIouxZSe17mzy8KbEAtHIyrTteJs5+syxkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6104314252113f899eb353c06723274d0e77bc799d2f1025d2eddbf76e679e66","last_reissued_at":"2026-07-05T07:51:59.513970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:59.513970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RegionGPT: Towards Region Understanding Vision Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxu Yin, Ka Chun Cheung, Ping Luo, Qiushan Guo, Shalini De Mello, Sifei Liu, Wonmin Byeon, Yizhou Yu","submitted_at":"2024-03-04T18:58:08Z","abstract_excerpt":"Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions. To address this, we introduce RegionGPT (short as RGPT), a novel framework designed for complex region-level captioning and understanding. RGPT enhances the spatial awareness of regional representation with simple yet effective modifications to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02330","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/2403.02330/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":"2403.02330","created_at":"2026-07-05T07:51:59.514037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02330v1","created_at":"2026-07-05T07:51:59.514037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02330","created_at":"2026-07-05T07:51:59.514037+00:00"},{"alias_kind":"pith_short_12","alias_value":"MECDCQSSCE7Y","created_at":"2026-07-05T07:51:59.514037+00:00"},{"alias_kind":"pith_short_16","alias_value":"MECDCQSSCE7YTHVT","created_at":"2026-07-05T07:51:59.514037+00:00"},{"alias_kind":"pith_short_8","alias_value":"MECDCQSS","created_at":"2026-07-05T07:51:59.514037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17539","citing_title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU","json":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU.json","graph_json":"https://pith.science/api/pith-number/MECDCQSSCE7YTHVTKPAGOIZHJU/graph.json","events_json":"https://pith.science/api/pith-number/MECDCQSSCE7YTHVTKPAGOIZHJU/events.json","paper":"https://pith.science/paper/MECDCQSS"},"agent_actions":{"view_html":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU","download_json":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU.json","view_paper":"https://pith.science/paper/MECDCQSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02330&json=true","fetch_graph":"https://pith.science/api/pith-number/MECDCQSSCE7YTHVTKPAGOIZHJU/graph.json","fetch_events":"https://pith.science/api/pith-number/MECDCQSSCE7YTHVTKPAGOIZHJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU/action/storage_attestation","attest_author":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU/action/author_attestation","sign_citation":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU/action/citation_signature","submit_replication":"https://pith.science/pith/MECDCQSSCE7YTHVTKPAGOIZHJU/action/replication_record"}},"created_at":"2026-07-05T07:51:59.514037+00:00","updated_at":"2026-07-05T07:51:59.514037+00:00"}