{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EZJRNE3FRMAY5VSAM34EVAFZOQ","short_pith_number":"pith:EZJRNE3F","schema_version":"1.0","canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","source":{"kind":"arxiv","id":"2502.02589","version":1},"attestation_state":"computed","paper":{"title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Athar, Chenglin Yang, Liang-Chieh Chen, Linjie Yang, Qihang Yu, Xiaohui Shen, Xiaojie Jin, Xueqing Deng","submitted_at":"2025-02-04T18:59:46Z","abstract_excerpt":"This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panoptic masks, this dataset aims to overcome limitations in existing image-text datasets that often lack detailed, scene-comprehensive descriptions. The COCONut-PanCap dataset incorporates fine-grained, region-level captions grounded in panoptic segmentation masks, ensuring consistency and improving the detail of generated captions. Through human-edited, densely annotated descriptions, COCONut-PanCap supports improved tr"},"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":"2502.02589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"bbcdf55fdc07bb2d2bb942d23367ee37eec24498d9e80df5e8816b5892f71cb7","abstract_canon_sha256":"f6cdc8f606fc30ef72664c7cbcace40c88ab6bcc244979cf78a866809ea228c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:30.679155Z","signature_b64":"UYT+0a9h4S3zyQ6FjqiS9fgfP7yLExw7U9atHck79GmVO6F61lGIO1pP8hmy55r20TgdqXHe/Ciyq+cntQv2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","last_reissued_at":"2026-07-05T10:09:30.678673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:30.678673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Athar, Chenglin Yang, Liang-Chieh Chen, Linjie Yang, Qihang Yu, Xiaohui Shen, Xiaojie Jin, Xueqing Deng","submitted_at":"2025-02-04T18:59:46Z","abstract_excerpt":"This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panoptic masks, this dataset aims to overcome limitations in existing image-text datasets that often lack detailed, scene-comprehensive descriptions. The COCONut-PanCap dataset incorporates fine-grained, region-level captions grounded in panoptic segmentation masks, ensuring consistency and improving the detail of generated captions. Through human-edited, densely annotated descriptions, COCONut-PanCap supports improved tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02589","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/2502.02589/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":"2502.02589","created_at":"2026-07-05T10:09:30.678734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02589v1","created_at":"2026-07-05T10:09:30.678734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02589","created_at":"2026-07-05T10:09:30.678734+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZJRNE3FRMAY","created_at":"2026-07-05T10:09:30.678734+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZJRNE3FRMAY5VSA","created_at":"2026-07-05T10:09:30.678734+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZJRNE3F","created_at":"2026-07-05T10:09:30.678734+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/EZJRNE3FRMAY5VSAM34EVAFZOQ","json":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ.json","graph_json":"https://pith.science/api/pith-number/EZJRNE3FRMAY5VSAM34EVAFZOQ/graph.json","events_json":"https://pith.science/api/pith-number/EZJRNE3FRMAY5VSAM34EVAFZOQ/events.json","paper":"https://pith.science/paper/EZJRNE3F"},"agent_actions":{"view_html":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ","download_json":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ.json","view_paper":"https://pith.science/paper/EZJRNE3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02589&json=true","fetch_graph":"https://pith.science/api/pith-number/EZJRNE3FRMAY5VSAM34EVAFZOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZJRNE3FRMAY5VSAM34EVAFZOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/action/storage_attestation","attest_author":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/action/author_attestation","sign_citation":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/action/citation_signature","submit_replication":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/action/replication_record"}},"created_at":"2026-07-05T10:09:30.678734+00:00","updated_at":"2026-07-05T10:09:30.678734+00:00"}