{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JWJPCKFJTQIJBB2WJ77SYOYI2J","short_pith_number":"pith:JWJPCKFJ","schema_version":"1.0","canonical_sha256":"4d92f128a99c109087564fff2c3b08d2756ad17566d5db114d729d65dbec0a1e","source":{"kind":"arxiv","id":"2504.05305","version":1},"attestation_state":"computed","paper":{"title":"URECA: Unique Region Caption Anything","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Heeji Yoon, Jaewoo Jung, Junwan Kim, Sangbeom Lim, Seungryong Kim","submitted_at":"2025-04-07T17:59:44Z","abstract_excerpt":"Region-level captioning aims to generate natural language descriptions for specific image regions while highlighting their distinguishing features. However, existing methods struggle to produce unique captions across multi-granularity, limiting their real-world applicability. To address the need for detailed region-level understanding, we introduce URECA dataset, a large-scale dataset tailored for multi-granularity region captioning. Unlike prior datasets that focus primarily on salient objects, URECA dataset ensures a unique and consistent mapping between regions and captions by incorporating"},"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":"2504.05305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T17:59:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bb01777a48997b8aba27d128037080274b46243ac279263c07035d20a413a4d","abstract_canon_sha256":"f1dd520bf36b92492ddca38a3d6a73b81724719a4c5fd1ec04e8abe5a5b9bcb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:37.357450Z","signature_b64":"c0tCxzDv4eNSsaRGUVpuWSncYZBbRPuUPyu/7DKk6LvWy3Z5FbKLmt+UbZnXc8HTqhEGrplF8UIaFNQ6+g23AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d92f128a99c109087564fff2c3b08d2756ad17566d5db114d729d65dbec0a1e","last_reissued_at":"2026-07-05T10:45:37.356957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:37.356957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"URECA: Unique Region Caption Anything","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Heeji Yoon, Jaewoo Jung, Junwan Kim, Sangbeom Lim, Seungryong Kim","submitted_at":"2025-04-07T17:59:44Z","abstract_excerpt":"Region-level captioning aims to generate natural language descriptions for specific image regions while highlighting their distinguishing features. However, existing methods struggle to produce unique captions across multi-granularity, limiting their real-world applicability. To address the need for detailed region-level understanding, we introduce URECA dataset, a large-scale dataset tailored for multi-granularity region captioning. Unlike prior datasets that focus primarily on salient objects, URECA dataset ensures a unique and consistent mapping between regions and captions by incorporating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05305","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/2504.05305/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":"2504.05305","created_at":"2026-07-05T10:45:37.357018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05305v1","created_at":"2026-07-05T10:45:37.357018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05305","created_at":"2026-07-05T10:45:37.357018+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWJPCKFJTQIJ","created_at":"2026-07-05T10:45:37.357018+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWJPCKFJTQIJBB2W","created_at":"2026-07-05T10:45:37.357018+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWJPCKFJ","created_at":"2026-07-05T10:45:37.357018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14471","citing_title":"Dense360: Dense Understanding from Omnidirectional Panoramas","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J","json":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J.json","graph_json":"https://pith.science/api/pith-number/JWJPCKFJTQIJBB2WJ77SYOYI2J/graph.json","events_json":"https://pith.science/api/pith-number/JWJPCKFJTQIJBB2WJ77SYOYI2J/events.json","paper":"https://pith.science/paper/JWJPCKFJ"},"agent_actions":{"view_html":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J","download_json":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J.json","view_paper":"https://pith.science/paper/JWJPCKFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05305&json=true","fetch_graph":"https://pith.science/api/pith-number/JWJPCKFJTQIJBB2WJ77SYOYI2J/graph.json","fetch_events":"https://pith.science/api/pith-number/JWJPCKFJTQIJBB2WJ77SYOYI2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J/action/storage_attestation","attest_author":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J/action/author_attestation","sign_citation":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J/action/citation_signature","submit_replication":"https://pith.science/pith/JWJPCKFJTQIJBB2WJ77SYOYI2J/action/replication_record"}},"created_at":"2026-07-05T10:45:37.357018+00:00","updated_at":"2026-07-05T10:45:37.357018+00:00"}