{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MECDCQSSCE7YTHVTKPAGOIZHJU","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":"08bbdfd58fb10d6b127c93c5266898e6f296d916b6c5d39ab58e8641e50684a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:58:08Z","title_canon_sha256":"5460d0e06c1057e684f2b242c5ac95eae2d2a92b4020f3bb36972095bae1f691"},"schema_version":"1.0","source":{"id":"2403.02330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02330","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02330v1","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02330","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"MECDCQSSCE7Y","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"MECDCQSSCE7YTHVT","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"MECDCQSS","created_at":"2026-07-05T07:51:59Z"}],"graph_snapshots":[{"event_id":"sha256:28ceb8758e09cb50e535a399a1db70c99b5d27cf0708b6341da0e6eddf4838e6","target":"graph","created_at":"2026-07-05T07:51:59Z","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/2403.02330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongxu Yin, Ka Chun Cheung, Ping Luo, Qiushan Guo, Shalini De Mello, Sifei Liu, Wonmin Byeon, Yizhou Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02330","kind":"arxiv","version":1},"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:e2bf61fbba3d04bef8c849edaad7808e58ab9422b2c2a53af309a8cfa6986691","target":"record","created_at":"2026-07-05T07:51:59Z","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":"08bbdfd58fb10d6b127c93c5266898e6f296d916b6c5d39ab58e8641e50684a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:58:08Z","title_canon_sha256":"5460d0e06c1057e684f2b242c5ac95eae2d2a92b4020f3bb36972095bae1f691"},"schema_version":"1.0","source":{"id":"2403.02330","kind":"arxiv","version":1}},"canonical_sha256":"6104314252113f899eb353c06723274d0e77bc799d2f1025d2eddbf76e679e66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6104314252113f899eb353c06723274d0e77bc799d2f1025d2eddbf76e679e66","first_computed_at":"2026-07-05T07:51:59.513970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:59.513970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gk4JaPFi7qwLT/hV2mbs5jv1jw3fzRh2nN4uPjOl+Eob61G+1lQIouxZSe17mzy8KbEAtHIyrTteJs5+syxkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:59.514471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2bf61fbba3d04bef8c849edaad7808e58ab9422b2c2a53af309a8cfa6986691","sha256:28ceb8758e09cb50e535a399a1db70c99b5d27cf0708b6341da0e6eddf4838e6"],"state_sha256":"b573d8b66e4e615c926764b7b1582caf2b0e95fc656bfb00bdd974ac2f73e976"}