{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OHPME3WUSGNVV2HG6W4KKQMNQD","short_pith_number":"pith:OHPME3WU","canonical_record":{"source":{"id":"2506.24102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:51:25Z","cross_cats_sorted":[],"title_canon_sha256":"063da9fcb3c37c46a432e40482fdaff546459f3f1da81819c74ecae18afbf134","abstract_canon_sha256":"44ff2dbcba4ce040012a6c4bf30a124ef404a9717e7420696e53fbfd24e0f637"},"schema_version":"1.0"},"canonical_sha256":"71dec26ed4919b5ae8e6f5b8a5418d80de2576a8c8d08e3c5d80c5bc21eb0fb2","source":{"kind":"arxiv","id":"2506.24102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.24102","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.24102v1","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24102","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"OHPME3WUSGNV","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"OHPME3WUSGNVV2HG","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"OHPME3WU","created_at":"2026-07-05T11:29:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OHPME3WUSGNVV2HG6W4KKQMNQD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.24102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:51:25Z","cross_cats_sorted":[],"title_canon_sha256":"063da9fcb3c37c46a432e40482fdaff546459f3f1da81819c74ecae18afbf134","abstract_canon_sha256":"44ff2dbcba4ce040012a6c4bf30a124ef404a9717e7420696e53fbfd24e0f637"},"schema_version":"1.0"},"canonical_sha256":"71dec26ed4919b5ae8e6f5b8a5418d80de2576a8c8d08e3c5d80c5bc21eb0fb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:33.149189Z","signature_b64":"6oO1YS8oK76n/O2ji+Nr3enJdeA87jtsyT/ax/FrOh9K5keAB5xu5i5N8p/Kh/beF7Z6L5ebk69mrw2DiISZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71dec26ed4919b5ae8e6f5b8a5418d80de2576a8c8d08e3c5d80c5bc21eb0fb2","last_reissued_at":"2026-07-05T11:29:33.148672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:33.148672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.24102","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":"2026-07-05T11:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wKRORzWBb/u8UIES10oHJ8S21GL+v7X4Ao/x1PIfgS5C5oYVBvqDziEWGLIQMEwOKTyhFcC0fJ4/MFAD2rzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:04:10.326073Z"},"content_sha256":"4f827b20c66e0ee9e07b2d5c602a545b7355c93224cc21ccb62590ebfbb5e58e","schema_version":"1.0","event_id":"sha256:4f827b20c66e0ee9e07b2d5c602a545b7355c93224cc21ccb62590ebfbb5e58e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OHPME3WUSGNVV2HG6W4KKQMNQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang Shi, Haobo Yuan, Jiahao Meng, Jiashi Feng, Lu Qi, Shihao Chen, Shilin Xu, Tao Zhang, Tianheng Cheng, Wenhao Huang, Xiangtai Li, Yanwei Li, Yikang Zhou, Yi Lin, Yueyi Sun, Zilong Huang","submitted_at":"2025-06-30T17:51:25Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill this gap for the community, we present DenseWorld-1M, the first massive, detailed, dense grounded caption dataset in the real world. We design a three-stage labeling pipeline, containing open-world per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24102","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/2506.24102/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":"2026-07-05T11:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuVk+Sr3pVNQPwRvAmvRFb2ltJxM71ag6+PUpDblV+/Paw2/HrW/2+1y7bhax+z0r35PKM99uipkkTPCZzkNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:04:10.326454Z"},"content_sha256":"e899208dc702a4bdb1807f5264377bc8ebfc8c31d6b5f59f6d66a78ea98f9168","schema_version":"1.0","event_id":"sha256:e899208dc702a4bdb1807f5264377bc8ebfc8c31d6b5f59f6d66a78ea98f9168"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/bundle.json","state_url":"https://pith.science/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/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":"2026-08-19T00:04:10Z","links":{"resolver":"https://pith.science/pith/OHPME3WUSGNVV2HG6W4KKQMNQD","bundle":"https://pith.science/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/bundle.json","state":"https://pith.science/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHPME3WUSGNVV2HG6W4KKQMNQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OHPME3WUSGNVV2HG6W4KKQMNQD","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":"44ff2dbcba4ce040012a6c4bf30a124ef404a9717e7420696e53fbfd24e0f637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:51:25Z","title_canon_sha256":"063da9fcb3c37c46a432e40482fdaff546459f3f1da81819c74ecae18afbf134"},"schema_version":"1.0","source":{"id":"2506.24102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.24102","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.24102v1","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24102","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"OHPME3WUSGNV","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"OHPME3WUSGNVV2HG","created_at":"2026-07-05T11:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"OHPME3WU","created_at":"2026-07-05T11:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:e899208dc702a4bdb1807f5264377bc8ebfc8c31d6b5f59f6d66a78ea98f9168","target":"graph","created_at":"2026-07-05T11:29:33Z","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/2506.24102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill this gap for the community, we present DenseWorld-1M, the first massive, detailed, dense grounded caption dataset in the real world. We design a three-stage labeling pipeline, containing open-world per","authors_text":"Guang Shi, Haobo Yuan, Jiahao Meng, Jiashi Feng, Lu Qi, Shihao Chen, Shilin Xu, Tao Zhang, Tianheng Cheng, Wenhao Huang, Xiangtai Li, Yanwei Li, Yikang Zhou, Yi Lin, Yueyi Sun, Zilong Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:51:25Z","title":"DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24102","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":"sha256:4f827b20c66e0ee9e07b2d5c602a545b7355c93224cc21ccb62590ebfbb5e58e","target":"record","created_at":"2026-07-05T11:29:33Z","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":"44ff2dbcba4ce040012a6c4bf30a124ef404a9717e7420696e53fbfd24e0f637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:51:25Z","title_canon_sha256":"063da9fcb3c37c46a432e40482fdaff546459f3f1da81819c74ecae18afbf134"},"schema_version":"1.0","source":{"id":"2506.24102","kind":"arxiv","version":1}},"canonical_sha256":"71dec26ed4919b5ae8e6f5b8a5418d80de2576a8c8d08e3c5d80c5bc21eb0fb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71dec26ed4919b5ae8e6f5b8a5418d80de2576a8c8d08e3c5d80c5bc21eb0fb2","first_computed_at":"2026-07-05T11:29:33.148672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:33.148672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6oO1YS8oK76n/O2ji+Nr3enJdeA87jtsyT/ax/FrOh9K5keAB5xu5i5N8p/Kh/beF7Z6L5ebk69mrw2DiISZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:33.149189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.24102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f827b20c66e0ee9e07b2d5c602a545b7355c93224cc21ccb62590ebfbb5e58e","sha256:e899208dc702a4bdb1807f5264377bc8ebfc8c31d6b5f59f6d66a78ea98f9168"],"state_sha256":"0ee90dc89428b3c74269975e56e460ccaff42f92f7165f79287bdbcda925f9e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsB2HyIx4hsydNto7YjasASg9g9QVqkrWVgft1Ai9Uh4cEB18/Lbgfgt0xJXOYOB37ScKUFa2xLHT0j0NzJuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:04:10.328840Z","bundle_sha256":"09247fabc5e6ceb0064bb27540d817ba1e3c3d1a13cfe2743bda5dd296c344f8"}}