{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EZJRNE3FRMAY5VSAM34EVAFZOQ","short_pith_number":"pith:EZJRNE3F","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"},"canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","source":{"kind":"arxiv","id":"2502.02589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02589","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02589v1","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02589","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"EZJRNE3FRMAY","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"EZJRNE3FRMAY5VSA","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"EZJRNE3F","created_at":"2026-07-05T10:09:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EZJRNE3FRMAY5VSAM34EVAFZOQ","target":"record","payload":{"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"},"canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","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"},"source_kind":"arxiv","source_id":"2502.02589","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZgMwDiOtxS01K6dhxTjkP4Yv5KBjgOqn/F9kjmYeK2JRSekPl0k8rzaSJwkSeoUfpFc6QBD0MygwY83B7+CCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:23:55.959724Z"},"content_sha256":"838620124a2719fc2cbe7ab252d22df20e356f94eb0a3b85a0eff09f0e725200","schema_version":"1.0","event_id":"sha256:838620124a2719fc2cbe7ab252d22df20e356f94eb0a3b85a0eff09f0e725200"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EZJRNE3FRMAY5VSAM34EVAFZOQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYDTyDCkHwRNF/cZg0rpazdwj6ALtiLbQDDQpb9GFHN6xk/ez79cNJnAD6DRjk9xIS5SHPTRtbUcnyjBBcrOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:23:55.960132Z"},"content_sha256":"18ef045671bbb1702feee407f1778fe5600a48c2f1b6fa2fa06127016fda7fd3","schema_version":"1.0","event_id":"sha256:18ef045671bbb1702feee407f1778fe5600a48c2f1b6fa2fa06127016fda7fd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/bundle.json","state_url":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T23:23:55Z","links":{"resolver":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ","bundle":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/bundle.json","state":"https://pith.science/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZJRNE3FRMAY5VSAM34EVAFZOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EZJRNE3FRMAY5VSAM34EVAFZOQ","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":"f6cdc8f606fc30ef72664c7cbcace40c88ab6bcc244979cf78a866809ea228c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:59:46Z","title_canon_sha256":"bbcdf55fdc07bb2d2bb942d23367ee37eec24498d9e80df5e8816b5892f71cb7"},"schema_version":"1.0","source":{"id":"2502.02589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02589","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02589v1","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02589","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"EZJRNE3FRMAY","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"EZJRNE3FRMAY5VSA","created_at":"2026-07-05T10:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"EZJRNE3F","created_at":"2026-07-05T10:09:30Z"}],"graph_snapshots":[{"event_id":"sha256:18ef045671bbb1702feee407f1778fe5600a48c2f1b6fa2fa06127016fda7fd3","target":"graph","created_at":"2026-07-05T10:09:30Z","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/2502.02589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Athar, Chenglin Yang, Liang-Chieh Chen, Linjie Yang, Qihang Yu, Xiaohui Shen, Xiaojie Jin, Xueqing Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:59:46Z","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02589","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":"sha256:838620124a2719fc2cbe7ab252d22df20e356f94eb0a3b85a0eff09f0e725200","target":"record","created_at":"2026-07-05T10:09:30Z","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":"f6cdc8f606fc30ef72664c7cbcace40c88ab6bcc244979cf78a866809ea228c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T18:59:46Z","title_canon_sha256":"bbcdf55fdc07bb2d2bb942d23367ee37eec24498d9e80df5e8816b5892f71cb7"},"schema_version":"1.0","source":{"id":"2502.02589","kind":"arxiv","version":1}},"canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26531693658b018ed64066f84a80b974339ce256f85d39b40caff7e86445df7e","first_computed_at":"2026-07-05T10:09:30.678673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:30.678673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UYT+0a9h4S3zyQ6FjqiS9fgfP7yLExw7U9atHck79GmVO6F61lGIO1pP8hmy55r20TgdqXHe/Ciyq+cntQv2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:30.679155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:838620124a2719fc2cbe7ab252d22df20e356f94eb0a3b85a0eff09f0e725200","sha256:18ef045671bbb1702feee407f1778fe5600a48c2f1b6fa2fa06127016fda7fd3"],"state_sha256":"3d26b154c9d031005392b491226c85f11bac40157eec80c9f53b6162fa31e8ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOAYjB2SeP9CO4Ps0bXlsFDHLf8okLkmM4eDxMpwZodDZGB2riloR5yImvMvaQ9dZ9CkICJlp/a2BcXuxc7CAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:23:55.962196Z","bundle_sha256":"ac33e44e1b7d79206ee5f6639d394307c73885a4cfbaabfb473be1e237f81254"}}